LOW-RESOURCE LANGUAGES

Language Clustering for Multilingual Named Entity Recognition (2021.findings-emnlp)

Challenge:	Automated headline generation systems have the potential to assist editors in finding interesting headlines to attract visitors or readers.
Approach:	They propose to use Bengali news article-headline pairings with auxiliary data to better model headline generation using pre-trained language models.
Outcome:	The proposed model improves on a Bengali news headline generation dataset by 3 to 10 percentage points over baselines.

Copied to clipboard

Kyle Shaffer

SARAL: A Low-Resource Cross-Lingual Domain-Focused Information Retrieval System for Effective Rapid Document Triage (P19-3)

Challenge:	Recent work in multilingual natural language processing has shown progress on tasks such as natural language inference and joint multilingual translation.
Approach:	They propose a technique that groups similar languages together by embeddings from a pre-trained masked language model and automatically discovering language clusters in this embeddable space.
Outcome:	The proposed technique outperforms baselines on 15 languages in the WikiAnn dataset showing meaningful multilingual transfer for low-resource languages (Swahili and Yoruba).

Copied to clipboard

Elizabeth Boschee, Joel Barry, Jayadev Billa, Marjorie Freedman, Thamme Gowda, Constantine Lignos, Chester Palen-Michel, Michael Pust, Banriskhem Kayang Khonglah, Srikanth Madikeri, Jonathan May, Scott Miller

Table Question Answering for Low-resourced Indic Languages (2024.emnlp-main)

Challenge:	a new cross-lingual information retrieval system for low-resource languages is available in less-frequently-taught languages . a multilingual system can search for relevant information in a haystack of documents in swahili or Somali . human-driven approaches to this problem are complicated in 'low-resourced' languages aaron sagar: "the key role played by humans in triaging results is complicated"
Approach:	They propose an end-to-end cross-lingual information retrieval system for low-resource languages . the system enables English speakers to search foreign language repositories using English queries . it summarizes the retrieved documents in English with respect to a particular information need .
Outcome:	The proposed system achieves top performance in the most recent IARPA MATERIAL CLIR+summarization evaluations.

Copied to clipboard

Vaishali Pal, Evangelos Kanoulas, Andrew Yates, Maarten Rijke

Structured Data in NLP

Challenge:	TableQA is the task of answering questions over tables of structured information, returning individual cells or tables as output.
Approach:	They propose a fully automatic large-scale tableQA data generation process for low-resource languages with limited budget.
Outcome:	The proposed method outperforms state-of-the-art LLMs on two Indic languages with no tableQA datasets and models on different aspects including mathematical reasoning capabilities and zero-shot cross-lingual transfer.

Continuous Model Improvement for Language Understanding with Machine Translation (2021.naacl-industry)

Copied to clipboard

Abdalghani Abujabal, Claudio Delli Bovi, Sungho Ryu, Turan Gojayev, Fabian Triefenbach, Yannick Versley

What is it? Towards a Generalizable Native American Language Identification System (2025.naacl-srw)

Challenge:	a simple translation-test approach would fail the latency requirements of a live environment.
Approach:	They show that annotating unlabeled utterances offline can improve performance . they demonstrate that an extrinsic evaluation can improve the performance if manual data is available .
Outcome:	The proposed method improves performance in an extrinsic evaluation setting with real-world commercial dialog system in german.

Copied to clipboard

Ivory Yang, Weicheng Ma, Carlos Guerrero Alvarez, William Dinauer, Soroush Vosoughi

Translating a Language You Don’t Know In the Chinese Room (P18-4)

Challenge:	Despite their cultural and historical significance, Native American languages remain unsupported by major commercial language identification systems.
Approach:	They propose to curate linguistic resources across all Native American languages for robust training and tailor data augmentation to generate synthetic yet linguistically coherent training samples.
Outcome:	The proposed system would be generalizable across all Native American languages . it would also generate coherent training samples for low-resource languages based on Plains Apache .

Copied to clipboard

Ulf Hermjakob, Jonathan May, Michael Pust, Kevin Knight

CVIT’s submissions to WAT-2019 (D19-52)

Challenge:	In a corruption of John Searle’s famous AI thought experiment, the Chinese Room, we enable humans to translate text even if they don’t have any prior knowledge of the source language.
Approach:	They propose a tool that allows humans to translate text without prior knowledge of the source language.
Outcome:	The Chinese Room tool can create fluent translations with human expertise required only for the target language.

Copied to clipboard

Jerin Philip, Shashank Siripragada, Upendra Kumar, Vinay Namboodiri, C V Jawahar

Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide (2026.tacl-1)

Challenge:	In this paper, we explore multiway-models for Indian languages.
Approach:	They propose to use a Transformer architecture to experiment with multilingual models and methods for low-resource languages.
Outcome:	The proposed system is feasible in low-resource languages.

Copied to clipboard

Marton Szep, Daniel Rueckert, Rüdiger von Eisenhart-Rothe, Florian Hinterwimmer

Improving Parallel Sentence Mining for Low-Resource and Endangered Languages (2025.acl-short)

Challenge:	Pre-trained language models provide strong foundations, but effective adaptation under data scarcity requires efficient and efficient fine-tuning techniques.
Approach:	They propose to review parameter-efficient fine-tuning techniques that lower training and deployment costs and domain and cross-lingual adaptation methods for both encoder and decoder models.
Outcome:	The proposed techniques lower training and deployment costs, domain and cross-lingual adaptation methods, and model specialization strategies.

Copied to clipboard

Shu Okabe, Katharina Hämmerl, Alexander Fraser

Alligators All Around: Mitigating Lexical Confusion in Low-resource Machine Translation (2025.naacl-short)

Challenge:	Parallel sentence mining is a technique used to find matching sentence pairs from a source and target language.
Approach:	They propose a benchmark dataset for parallel sentence mining on three low-resource languages . they apply alignment post-processing and cluster-based isotropy enhancement techniques to one of them .
Outcome:	The proposed datasets show better mining quality overall for low-resource languages . the proposed methods are crucial for optimizing parallel data extraction for low resource languages - a new study shows.

Copied to clipboard

Elizabeth Nielsen, Isaac Rayburn Caswell, Jiaming Luo, Colin Cherry

GameQA: Gamified Mobile App Platform for Building Multiple-Domain Question-Answering Datasets (2023.eacl-demo)

Challenge:	Current machine translation systems for low-resource languages have a particular failure mode: they tend to confuse words within a domain.
Approach:	They propose a recall-based metric to measure the failure mode of machine translation systems for low-resource languages.
Outcome:	The proposed model outperforms a lexicon-based translator in 122 low-resource languages.

Copied to clipboard

Njall Skarphedinsson, Breki Gudmundsson, Steinar Smari, Marta Kristin Larusdottir, Hafsteinn Einarsson, Abuzar Khan, Eric Nyberg, Hrafn Loftsson

How many words does it take to understand a low-resource language? (2025.naacl-srw)

Challenge:	a common problem with question-answering datasets is that they require annotators to source answers from the internet . a crowd-sourcing platform is available for low-resource languages, but it is limited in terms of information available.
Approach:	They propose a crowd-sourcing platform to gather multiple-domain QA data for low-resource languages.
Outcome:	The proposed platform rivals large QA datasets for high-resource languages in size and answerability.

Copied to clipboard

Emily Chang, Nada Basit

Exploring Multilingual Syntactic Sentence Representations (D19-55)

Challenge:	We evaluated the documentation needed to create a sentence embedding space using widely spoken languages.
Approach:	They propose to use widely spoken languages as a proxy for low-resource languages to evaluate the documentation needed to create a sentence embedding space.
Outcome:	The proposed language model can be used to improve the performance of sentences embedded in low-resource languages.

Copied to clipboard

Chen Liu, Anderson De Andrade, Muhammad Osama

Representation Learning

Challenge:	Recent studies on language models that learn syntactic information focus on learning the semantic structures of language.
Approach:	They propose to use a multilingual parallel corpus augmented by universal part-of-speech tags to learn syntactic sentence embeddings.
Outcome:	The proposed method performs better than state-of-the-art language models in low-resource languages.

SwahBERT: Language Model of Swahili (2022.naacl-main)

Copied to clipboard

Gati Martin, Medard Edmund Mswahili, Young-Seob Jeong, Jiyoung Woo

Can Uniform Meaning Representation Help GPT-4 Translate from Indigenous Languages? (2025.acl-short)

Challenge:	Social media and Internet forums are valuable sources of citizens’ opinions, which can be analyzed for community development and user behavior analysis.
Approach:	They present a pre-training and annotated datasets of Swahili and an emotion classification datasets that are manually annotating by two native Swahils.
Outcome:	The proposed model outperforms existing monolingual language model in almost all downstream tasks.

Copied to clipboard

Shira Wein

Hate Speech and Offensive Language Detection in Bengali (2022.aacl-main)

Challenge:	In this study, we examine the downstream utility of Uniform Meaning Representation (UMR) for low-resource languages.
Approach:	They explore the utility of Uniform Meaning Representation (UMR) for low-resource languages by incorporating it into GPT-4 prompts.
Outcome:	The proposed model performs better than existing models in Navajo, Arápaho, and Kukama with and without demonstrations and annotations.

Copied to clipboard

Mithun Das, Somnath Banerjee, Punyajoy Saha, Animesh Mukherjee

Information Retrieval

Challenge:	Existing research on hate speech detection in English does not cover low-resource languages like Bengali.
Approach:	They develop an annotated dataset of 10K Bengali posts consisting of 5K actual and 5K Romanized Bengali tweets.
Outcome:	The proposed model outperforms other models on training actual and romanized datasets by interpreting the semantic expressions better.

Unsupervised Multilingual Word Embeddings (D18-1)

Copied to clipboard

Xilun Chen, Claire Cardie

LLMs Are Few-Shot In-Context Low-Resource Language Learners (2024.naacl-long)

Challenge:	Prior art for learning UMWEs relies on a number of independently trained UBWEs to obtain multilingual embeddings.
Approach:	They propose a fully unsupervised framework that exploits the relations between all language pairs to learn multilingual embeddings without cross-lingual supervision.
Outcome:	The proposed framework outperforms supervised approaches on multilingual word translation and cross-lingual word similarity and beats a number of other approaches trained with cross-linguistic resources.

Copied to clipboard

Samuel Cahyawijaya, Holy Lovenia, Pascale Fung

Low-Resource Name Tagging Learned with Weakly Labeled Data (D19-1)

Challenge:	In-context learning (ICL) empowers large language models to perform diverse tasks in underrepresented languages using only short in-contrast information.
Approach:	They extensively assess the effectiveness of in-context learning with LLMs in low-resource languages . they also identify the shortcomings of in context label alignment .
Outcome:	The proposed approach improves understanding quality of low-resource languages by closing the language gap in the target language.

Copied to clipboard

Yixin Cao, Zikun Hu, Tat-seng Chua, Zhiyuan Liu, Heng Ji

The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification (2020.findings-emnlp)

Challenge:	Existing methods for name tagging in low-resource languages or domains require extensive human efforts for training annotations.
Approach:	They propose a neural model for name tagging based on weakly labeled (WL) data.
Outcome:	The proposed model outperforms existing models in five low-resource languages and fine-grained food domains and shows that it is more efficient and efficient than existing models.

Copied to clipboard

Abdullatif Köksal, Arzucan Özgür

Transfer Learning Based Free-Form Speech Command Classification for Low-Resource Languages (P19-2)

Challenge:	Current approaches for relation classification are focused on the English language and require lots of training data with human annotations.
Approach:	They propose a baseline model based on Multilingual BERT and a new multilingual pretraining setup . they propose 'relationship classification' models that use distant supervision .
Outcome:	The proposed model significantly improves the baseline model with distant supervision.

Copied to clipboard

Yohan Karunanayake, Uthayasanker Thayasivam, Surangika Ranathunga

MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning (2021.naacl-main)

Challenge:	Current speech-based user interfaces use data intensive methodologies to recognize free-form speech commands, but this is not viable for low-resource languages, which lack speech data.
Approach:	They propose a method to develop a domain-specific speech command classification system using speech data from a high-resource language.
Outcome:	The proposed system is robust to low-resource languages with limited speech data . the proposed system achieves significant results for Sinhala and Tamil datasets .

Copied to clipboard

Mengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Hassan Awadallah

Annotation-Efficient Vision-Language Model Adaptation to the Polish Language Using the LLaVA Framework (2026.eacl-srw)

Challenge:	Recent work shows that multilingual representations are disjointed across languages, bringing additional challenges for transfer onto extremely low-resource languages.
Approach:	They propose a meta-learning based framework that learns to transform representations judiciously from auxiliary languages to a target one and brings their representation spaces closer for effective transfer.
Outcome:	The proposed framework learns to transform representations from auxiliary languages to a target language and brings their representation spaces closer for effective transfer.

Copied to clipboard

Grzegorz Statkiewicz, Alicja Dobrzeniecka, Karolina Seweryn, Aleksandra Krasnodębska, Karolina Piosek, Katarzyna Bogusz, Sebastian Cygert, Wojciech Kusa

Post-ASR Correction in Hindi: Comparing Language Models and Large Language Models in Low-Resource Scenarios (2026.eacl-short)

Challenge:	Currently, most vision-language models are trained on English-centric data, limiting their usability for non-English-speaking users.
Approach:	They reproduce and adapt LLaVA-Next methodology to create Polish VLMs . they use a fully automated pipeline for translating and filtering existing multimodal datasets based on Polish data for OCR and culturally specific tasks.
Outcome:	The proposed model improves on a Polish-adapted model and shows higher quality captions in generative evaluations.

Copied to clipboard

Rishabh Kumar, Amrith Krishna, Ganesh Ramakrishnan, Preethi Jyothi

Efficient Low-Resource Language Models Using Tokenizer Transfer (2026.eacl-srw)

Challenge:	Automatic Speech Recognition (ASR) systems for low-resource languages produce erroneous transcripts due to limited annotated data and linguistic complexity.
Approach:	They compare language models and large language models for post-ASR correction in Hindi . they observe a scaling trend under zero-shot ICL where mid-sized LLMs degrade performance before marginal recovery at extreme scales.
Outcome:	The proposed model outperforms larger models in both fine-tuning and in-context learning settings.

Copied to clipboard

Gustaf Gren, Murathan Kurfali

Chain-of-Dictionary Prompting Elicits Translation in Large Language Models (2024.emnlp-main)

Challenge:	Tokenizer transfer allows training a model for low-resource languages without full retraining . a study of pre-trained tokenizers shows that they are more efficient than traditional training methods.
Approach:	They evaluate tokenizer transfer on models trained on language-specific corpora, Orthogonal Mapping Pursuit and Fast Vocabulary Transfer.
Outcome:	The proposed model adapts to a pre-trained model without full retraining and improves cross-lingual applicability.

Copied to clipboard

Hongyuan Lu, Haoran Yang, Haoyang Huang, Dongdong Zhang, Wai Lam, Furu Wei

How Good is Zero-Shot MT Evaluation for Low Resource Indian Languages? (2024.acl-short)

Challenge:	Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation . yet, they struggle with translating low-resource languages.
Approach:	They propose a framework that chained multilingual dictionaries to elicit translation abilities for LLMs . they show that CoD can significantly improve LLM translation by evoking more information .
Outcome:	The proposed framework improves on ChatGPT and InstructGPT's translation abilities.

Copied to clipboard

Anushka Singh, Ananya Sai, Raj Dabre, Ratish Puduppully, Anoop Kunchukuttan, Mitesh Khapra

LionGuard: A Contextualized Moderation Classifier to Tackle Localized Unsafe Content (2025.coling-industry)

Challenge:	a recent study focused on machine translation evaluation for low-resource languages . linguistic aspects that vary across languages are factors that will exacerbate the problem in low-source languages due to the reliance on extensive data resources.
Approach:	They propose to use multi-dimensional quality metrics and DA annotations to meta-evaluate MT evaluation metrics for low-resource languages.
Outcome:	The proposed evaluation metrics are based on human scores on the candidate translations of assamese, maithili, and Punjabi.

Copied to clipboard

Jessica Foo, Shaun Khoo

Text Classification

Challenge:	Existing moderation classes that perform well on English may not perform well in Singlish.
Approach:	They propose a Singapore-contextualized moderation classifier that can guard against unsafe LLM usage.
Outcome:	The proposed class outperforms existing modes on Singlish data by 14% and up to 51%.

Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data (2021.acl-long)

Copied to clipboard

Wei-Jen Ko, Ahmed El-Kishky, Adithya Renduchintala, Vishrav Chaudhary, Naman Goyal, Francisco Guzmán, Pascale Fung, Philipp Koehn, Mona Diab

Developing multilingual speech synthesis system for Ojibwe, Mi’kmaq, and Maliseet (2025.naacl-short)

Challenge:	linguistic overlap between low-resource languages and high-resourced languages is a major obstacle for training high-quality machine translation systems.
Approach:	They exploit linguistic overlap to facilitate translation to and from low-resource languages . they use monolingual data and parallel data in related high-resourced languages based on their method .
Outcome:	The proposed method significantly improves translation into low-resource language compared to baselines on 7 languages from three different language families.

Copied to clipboard

Shenran Wang, Changbing Yang, Michael l Parkhill, Chad Quinn, Christopher Hammerly, Jian Zhu

ViGPTQA - State-of-the-Art LLMs for Vietnamese Question Answering: System Overview, Core Models Training, and Evaluations (2023.emnlp-industry)

Challenge:	In general, speech synthesis for Indigenous languages is underdeveloped compared to the majority of languages.
Approach:	They propose to train a multilingual model on three typologically similar languages to improve performance over monolingual models.
Outcome:	The proposed model can train on three similar languages with high performance and is highly competitive with self-attention architectures with higher memory efficiency.

Copied to clipboard

Minh Thuan Nguyen, Khanh Tung Tran, Nhu Van Nguyen, Xuan-Son Vu

Question Answering

Challenge:	Large language models (LLMs) and their applications in low-resource languages are limited due to lack of training data and benchmarking datasets.
Approach:	They propose a question-response system for Vietnamese that uses LLMs . they propose to open-source the model and train it on benchmark datasets based on Vietnamese data .
Outcome:	The proposed question answering system for Vietnamese is open-source and performant . it can learn and capture human-like text, but there is a gap in evaluations for Vietnamese .

Cross-lingual Text Classification with Heterogeneous Graph Neural Network (2021.acl-short)

Copied to clipboard

Ziyun Wang, Xuan Liu, Peiji Yang, Shixing Liu, Zhisheng Wang

Handling Cross- and Out-of-Domain Samples in Thai Word Segmentation (2021.findings-acl)

Challenge:	Existing methods for cross-lingual text classification only consider factors beyond semantic similarity, causing performance degradation between some language pairs.
Approach:	They propose a method to incorporate heterogeneous information within and across languages for cross-lingual text classification using graph convolutional networks.
Outcome:	The proposed method significantly outperforms state-of-the-art models on all tasks and achieves consistent performance gain over baselines in low-resource settings.

Copied to clipboard

Peerat Limkonchotiwat, Wannaphong Phatthiyaphaibun, Raheem Sarwar, Ekapol Chuangsuwanich, Sarana Nutanong

Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval (2022.coling-1)

Challenge:	Word segmentation is domain-dependent, which can be a challenge in low-resource languages like Thai and Urdu . a framework to handle out-of-domain inputs is proposed to improve word segmentation .
Approach:	They propose a domaingeneric domain adaptation framework and data augmentation technique to combat low-resource problems.
Outcome:	The proposed model outperforms the state-of-the-art Thai word segmentation method in out-of domain scenarios.

Copied to clipboard

Robert Litschko, Ivan Vulić, Goran Glavaš

Mini But Mighty: Efficient Multilingual Pretraining with Linguistically-Informed Data Selection (2023.findings-eacl)

Challenge:	State-of-the-art neural rankers are notoriously data-hungry and rarely used in multilingual and cross-lingual retrieval settings.
Approach:	They propose to use Sparse Fine-Tuning Masks and Adapters to transfer rankers trained on English data to other languages and cross-lingual setups by means of multilingual encoders.
Outcome:	The proposed methods outperform standard zero-shot transfer with full MMT fine-tuning while being more modular and reducing training times.

Copied to clipboard

Tolulope Ogunremi, Dan Jurafsky, Christopher Manning

Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning (2025.acl-short)

Challenge:	AfriBERTa shows that training transformer models from scratch on 1GB of data from many unrelated African languages outperforms massively multilingual models on downstream NLP tasks.
Approach:	They propose that training on smaller amounts of data but from related languages could match the performance of models trained on large, unrelated data.
Outcome:	The proposed model outperforms models trained on large, unrelated datasets on downstream NLP tasks.

Copied to clipboard

Nathaniel Krasner, Nicholas Lanuzo, Antonios Anastasopoulos

Layer-wise Swapping for Generalizable Multilingual Safety (2026.eacl-long)

Challenge:	Multilingual alignment of sentence representations has mostly required bitexts to bridge the gap between languages.
Approach:	They propose to use image captions to implicitly align text representations between languages to make them usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval.
Outcome:	The proposed approach is usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval.

Copied to clipboard

Hyunseo Shin, Wonseok Hwang

Lessons from the Bible on Modern Topics: Low-Resource Multilingual Topic Model Evaluation (N18-1)

Challenge:	Existing safety datasets are predominantly English-centric, limiting progress in multilingual safety alignment.
Approach:	They propose a safety-aware layer swapping method that transfers alignment from an English safety expert to low-resource language experts without additional training.
Outcome:	The proposed method preserves performance on general language understanding tasks while enhancing safety in the target languages.

Copied to clipboard

Shudong Hao, Jordan Boyd-Graber, Michael J. Paul

Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity (2024.findings-eacl)

Challenge:	Existing metrics to evaluate multilingual topic quality are inadequate for multilingual document analysis.
Approach:	They propose a new intrinsic evaluation metric for multilingual topic models that correlates well with human judgments of multilingual coherence and performance in downstream applications.
Outcome:	The proposed model improves the performance of multilingual topic models in low-resource languages and with human judgments of multilinguistic topic coherence.

Copied to clipboard

Eric Khiu, Hasti Toossi, Jinyu Liu, Jiaxu Li, David Anugraha, Juan Flores, Leandro Roman, A. Seza Doğruöz, En-Shiun Lee

Memory-enhanced Large Language Model for Cross-lingual Dependency Parsing via Deep Hierarchical Syntax Understanding (2025.findings-emnlp)

Challenge:	Existing approaches for predicting the performance of NLP models for low-resource languages (LRLs) focus on high-resourced languages, overlooking LRLs and domain shifts.
Approach:	They investigate the impact of domain similarity on predicting performance of machine translation models in low-resource languages.
Outcome:	The results show that domain similarity has the most important impact on predicting the performance of Machine Translation models.

Copied to clipboard

Jianjian Liu, Ying Li, Zhengtao Yu, Shun Su, Shengxiang Gao, Yuxin Huang

Cyclical Contrastive Learning Based on Geodesic for Zero-shot Cross-lingual Spoken Language Understanding (2024.findings-acl)

Challenge:	Experimental results show that our approach can significantly improve the parsing accuracy of all baseline models, leading to new state-of-the-art results.
Approach:	They propose a deep hierarchical syntax understanding approach to improve the cross-lingual semantic memory capability of large language models by implicitly aligning linguistic knowledge between source and target languages.
Outcome:	The proposed approach improves the cross-lingual semantic memory capability of large language models by combining implicit multi-task fine-tuning and explicit label bank guiding.

Copied to clipboard

Xuxin Cheng, Zhihong Zhu, Bang Yang, Xianwei Zhuang, Hongxiang Li, Yuexian Zou

Low-Resource Counterspeech Generation for Indic Languages: The Case of Bengali and Hindi (2024.findings-eacl)

Challenge:	zero-shot cross-lingual SLU is a challenging task in low-resource languages . a lack of labeled training data makes it difficult to align representations of similar sentences .
Approach:	They propose a framework that uses cyclical contrastive learning to achieve consistency between languages . they propose to use geodesic to measure the similarity to construct positive and negative pairs .
Outcome:	The proposed framework achieves state-of-the-art performance on multiATIS++ and MTOP datasets.

Copied to clipboard

Mithun Das, Saurabh Pandey, Shivansh Sethi, Punyajoy Saha, Animesh Mukherjee

NeuronMoE: Efficient Cross-Lingual Extension via Neuron-Guided Mixture-of-Experts (2026.eacl-long)

Challenge:	NLP is a technique that generates counterspeech that “counters” the vicious tone of online abuse and dilutes/ameliorates their rippling effect over the social network.
Approach:	They propose to use neural architectures to generate counterspeech that can "counter" the vicious tone of online abuse and dilute/ameliorate their rippling effect over the social network.
Outcome:	The proposed model can generate counterspeech in monolingual setups and is more transferable when languages belong to the same language family.

Copied to clipboard

Rongzhi Li, Hitomi Yanaka

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)

Challenge:	Existing approaches allocate experts based on layer-level similarity, yet language processing exhibits fine-grained specialization at individual neurons.
Approach:	They propose a method that analyzes language-specific neurons to guide expert allocation per layer based on cross-lingual neuron diversity.
Outcome:	The proposed method reduces the complexity of the model by 40% while matching the performance of the LayerMoE baseline.

Copied to clipboard

Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen

A Systematic Analysis of Subwords and Cross-Lingual Transfer in Multilingual Translation (2024.findings-naacl)

Challenge:	GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages.
Approach:	They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement.
Outcome:	The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3.

Copied to clipboard

Francois Meyer, Jan Buys

OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages (2022.acl-long)

Challenge:	Multilingual modelling can improve machine translation for low-resource languages, partly through shared subword representations.
Approach:	They propose to use subword regularisation to promote synergy and BPE to facilitate cross-lingual transfer.
Outcome:	The proposed methods promote synergy and prevent interference across different linguistic typologies.

Copied to clipboard

Prem Selvaraj, Gokul Nc, Pratyush Kumar, Mitesh Khapra

ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual Summarization (2023.findings-acl)

Challenge:	a new study examines the performance of pretraining for sign language recognition in low-resource settings.
Approach:	They propose using pose extracted through pretrained models as the standard modality of data to reduce training time and enable efficient inference.
Outcome:	The proposed model reduces training time and allows efficient inference in sign languages.

Copied to clipboard

Peiyao Li, Zhengkun Zhang, Jun Wang, Liang Li, Adam Jatowt, Zhenglu Yang

A Tulu Resource for Machine Translation (2024.lrec-main)

Challenge:	Existing studies ignore data imbalance in multilingual settings and do not utilize monolingual data.
Approach:	They propose a cross-lingual summarization model that aligns cross-linguistic data with high-resource monolingual data via contrastive and consistency loss.
Outcome:	The proposed model outperforms baseline models and consistently dominates on 45 language pairs.

Copied to clipboard

Manu Narayanan, Noëmi Aepli

Challenge:	Using parallel datasets, we train a machine translation system in English–Tulu .
Approach:	They present a parallel dataset for English–Tulu translation using human translations into the multilingual machine translation resource FLORES-200.
Outcome:	The proposed model outperforms Google Translate by 19 BLEU points (in September 2023).

Urdu Word Embeddings (L18-1)

Copied to clipboard

Samar Haider

Local Word Discovery for Interactive Transcription (2021.emnlp-main)

Challenge:	Recent advances in distributional semantics have led to the rise of neural network-based models that use unsupervised learning to represent words as dense, distributed vectors, called 'word embeddings' embedders hold key to improving natural language processing for low-resource languages, since they require significant time and manpower.
Approach:	They train a skip-gram model on 140 million Urdu words to create the first large-scale word embeddings for the Urdu language.
Outcome:	The proposed models capture high degree of syntactic and semantic similarity between words and are able to generalize well on the Urdu translation task.

Copied to clipboard

William Lane, Steven Bird

Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource Languages (2022.acl-long)

Challenge:	a new computational task supports the construction of high quality texts and lexicons for low resource languages.
Approach:	They propose a computational task which is tuned to the available knowledge and interests in an Indigenous community.
Outcome:	The proposed method achieves a transcription density gain of 17% in a morphologically complex language . the proposed grammar includes a description of the phonology and morphosyntax .

Copied to clipboard

Xu Han, Yuqi Luo, Weize Chen, Zhiyuan Liu, Maosong Sun, Zhou Botong, Hao Fei, Suncong Zheng

Multilingual and cross-lingual document classification: A meta-learning approach (2021.eacl-main)

Challenge:	Experimental results show that by applying our framework, we can easily learn effective FGET models for low-resource languages.
Approach:	They propose a cross-lingual contrastive learning framework to learn FGET models for low-resource languages.
Outcome:	The proposed framework can learn effective FGET models for low-resource languages even without human-labeled data.

Copied to clipboard

Niels van der Heijden, Helen Yannakoudakis, Pushkar Mishra, Ekaterina Shutova

Information Retrieval

Challenge:	Existing methods to document classification in low-resource languages are under-resourced . 6% of the world's languages are spoken, and many have inadequate resources .
Approach:	They propose a meta-learning approach to document classification in low-resource languages . they propose 'nuclear-shot' cross-lingual adaptation to previously unseen languages based on limited data .
Outcome:	The proposed method performs on-par on some languages while under-resourced in others.

Detection of Human and Machine-Authored Fake News in Urdu (2025.acl-long)

Copied to clipboard

Muhammad Zain Ali, Yuxia Wang, Bernhard Pfahringer, Tony C Smith

Unsupervised Induction of Linguistic Categories with Records of Reading, Speaking, and Writing (N18-1)

Challenge:	Existing methods for fake news detection focus on binary classification and English texts, ignoring the distinction between machine-generated true vs. fake news and low-resource languages.
Approach:	They propose to include machine-generated news focusing on Urdu to improve accuracy and robustness.
Outcome:	The proposed strategy improves accuracy and robustness across four datasets in various settings.

Copied to clipboard

Maria Barrett, Ana Valeria González-Garduño, Lea Frermann, Anders Søgaard

Evaluation of Sentence Representations in Polish (2020.lrec-1)

Challenge:	a few researchers have shown that data traces from human processing can be used to improve NLP models.
Approach:	They propose to use data readily available for most languages to improve unsupervised induction . they find that english unsupervised POS induction achieves an error reduction of 1.5% .
Outcome:	The proposed model improves on Ontonotes domains with a word embeddings.

Copied to clipboard

Slawomir Dadas, Michał Perełkiewicz, Rafał Poświata

Representation Learning

Challenge:	Existing methods for learning sentence representations have been limited in low-resource languages such as Polish .
Approach:	They propose two new Polish datasets for evaluating sentence embeddings and evaluate eight different methods including Polish and multilingual models.
Outcome:	The proposed methods show strengths and weaknesses in Polish and multilingual models.

Multi-View Cross-Lingual Structured Prediction with Minimum Supervision (2021.acl-long)

Copied to clipboard

Zechuan Hu, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

Struct-XLM: A Structure Discovery Multilingual Language Model for Enhancing Cross-lingual Transfer through Reinforcement Learning (2023.emnlp-main)

Challenge:	Existing work on cross-lingual transfer learning focuses on transferring knowledge from high-resource languages to low-resourced ones.
Approach:	They propose a multi-view framework that integrates multiple source models into an aggregated source view and transfers it to a target view based on a task-specific model.
Outcome:	The proposed framework improves on three structured prediction tasks on 16 datasets.

Copied to clipboard

Linjuan Wu, Weiming Lu

A Scalable Framework for Automated NER Annotation Correction in Low-Resource Languages (2026.findings-eacl)

Challenge:	Existing methods require syntactic labels that are difficult to obtain and of poor quality for low-resource languages.
Approach:	They propose a syntactic alignment model that leverages reinforcement learning to discover universal syntaktic structures for cross-lingual PLM alignment.
Outcome:	The proposed model improves cross-lingual representation alignment on the XTREME benchmark.

Copied to clipboard

Toqeer Ehsan, Thamar Solorio

Document-Level Zero-Shot Relation Extraction with Entity Side Information (2026.eacl-long)

Challenge:	Existing NER benchmarks lack quality annotations, resulting in poor performance.
Approach:	They propose a frequency-based iterative approach that leverages self-training and a dual-threshold mechanism to enhance inference confidence.
Outcome:	The proposed approach improves NER performance on three datasets with a high number of missing annotations.

Copied to clipboard

Mohan Raj Chanthran, Lay-Ki Soon, Ong Huey Fang, Bhawani Selvaretnam

Breaking Down Multilingual Machine Translation (2022.findings-acl)

Challenge:	Existing approaches rely on Large Language Models (LLMs) to generate synthetic data for unseen labels.
Approach:	They propose a document-level zero-shot relation extraction framework with Entity Side Information to solve existing problems.
Outcome:	The proposed approach achieves an average improvement of 11.6% in the macro F1-Score compared to baseline models and existing benchmarks.

Copied to clipboard

Ting-Rui Chiang, Yi-Pei Chen, Yi-Ting Yeh, Graham Neubig

Unsupervised Abstractive Summarization of Bengali Text Documents (2021.eacl-main)

Challenge:	Multilingual training is an essential ingredient in machine translation systems . but it has different effects in different multilingual settings, such as many-to-one, one-tomany and many- to-many learning .
Approach:	They compare multilingual training settings with encoders and decoders initialized by multilingual learning . they find important attention heads for each language pair and compare their correlations during inference .
Outcome:	The proposed models outperform the best models for high-resource languages and one-to-many models for low-resourced languages.

Copied to clipboard

Radia Rayan Chowdhury, Mir Tafseer Nayeem, Tahsin Tasnim Mim, Md. Saifur Rahman Chowdhury, Taufiqul Jannat

Bilingual Sentiment Embeddings: Joint Projection of Sentiment Across Languages (P18-1)

Challenge:	Abstractive summarization systems are difficult to perform due to the unavailability of the parallel data for low-resource languages like Bengali.
Approach:	They propose a graph-based unsupervised abstractive summarization system in Bengali text documents that requires only a Part-Of-Speech (POS) tagger and a pre-trained language model trained on Bengali texts.
Outcome:	The proposed system outperforms baselines without human-annotated reference summaries on a human-random dataset with Bengali text.

Copied to clipboard

Jeremy Barnes, Roman Klinger, Sabine Schulte im Walde

Unsupervised Learning of PCFGs with Normalizing Flow (P19-1)

Challenge:	Existing approaches to sentiment analysis in low-resource languages lack annotated corpora or do not capture sentiment information.
Approach:	They propose a model that represents sentiment in a source and target language without annotated corpus.
Outcome:	The proposed model outperforms state-of-the-art methods on four out of six setups and captures complementary information to machine translation.

Copied to clipboard

Lifeng Jin, Finale Doshi-Velez, Timothy Miller, Lane Schwartz, William Schuler

Lost in Translation, Found in Spans: Identifying Claims in Multilingual Social Media (2023.emnlp-main)

Challenge:	Existing induction models unable to incorporate semantics and morphology into induction . current models lack a robust model for generating morphologically rich sentences .
Approach:	They propose a PCFG inducer which uses context embeddings to generalize over rare, morphologically rich forms.
Outcome:	The proposed model produces grammars with state-of-the-art accuracy on a variety of languages.

Copied to clipboard

Shubham Mittal, Megha Sundriyal, Preslav Nakov

Teaching LLMs to Abstain across Languages via Multilingual Feedback (2024.emnlp-main)

Challenge:	Claim span identification (CSI) is an important step in fact-checking pipelines . despite its importance to journalists and fact-seekers, it remains a understudied problem .
Approach:	They propose to use social media claims to identify text segments that contain a check-worthy claim or assertion in a social media post.
Outcome:	The proposed dataset outperforms other cross-lingual transfer methods on multiple languages.

Copied to clipboard

Shangbin Feng, Weijia Shi, Yike Wang, Wenxuan Ding, Orevaoghene Ahia, Shuyue Stella Li, Vidhisha Balachandran, Sunayana Sitaram, Yulia Tsvetkov

Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation (2021.findings-acl)

Challenge:	Existing studies on LLM abstention focus on English, but they show that it can reduce the accuracy of the model by 20.5% .
Approach:	They propose to teach LLMs to abstain in the face of knowledge gaps by generating multiple feedback items in related languages.
Outcome:	Extensive experiments show that the proposed approach outperforms baselines and achieves 9.2% improvement for low-resource languages.

Copied to clipboard

Zihan Liu, Genta Indra Winata, Pascale Fung

Textual Supervision for Visually Grounded Spoken Language Understanding (2020.findings-emnlp)

Challenge:	a lack of data in low-resource languages has limited the performance of a multilingual pre-trained model.
Approach:	They propose a continuous pre-training framework to adapt mBART to unseen languages . they construct noisy mixed-language text from the monolingual corpus of the target language .
Outcome:	The proposed framework improves finetuning performance on low-resource translation pairs . the proposed framework also improves on translation pairs where both languages are seen .

Copied to clipboard

Bertrand Higy, Desmond Elliott, Grzegorz Chrupała

Neural Factor Graph Models for Cross-lingual Morphological Tagging (P18-1)

Challenge:	a new approach to spoken language understanding extracts semantic information directly from speech without relying on transcriptions.
Approach:	They propose to use textual supervision to train visually-grounded models of spoken language understanding without relying on transcriptions.
Outcome:	The proposed model improves when enough text is available, the study shows . compared with pipeline-based models, the pipeline approach performs better when enough data is available .

Copied to clipboard

Chaitanya Malaviya, Matthew R. Gormley, Graham Neubig

Segmenting Subtitles for Correcting ASR Segmentation Errors (2021.eacl-main)

Challenge:	Existing approaches to morphological tagging are limited by the assumption that tag sets overlap . a limited amount of data is available for most languages to learn these morphology taggers.
Approach:	They propose a method for cross-lingual morphological tagging that relaxes this assumption . they use factorial conditional random fields with neural network potentials to smooth over superficial differences in the surface forms .
Outcome:	The proposed model can smooth over superficial differences in the surface forms and generate unseen or rare tag sets.

Copied to clipboard

David Wan, Chris Kedzie, Faisal Ladhak, Elsbeth Turcan, Petra Galuscakova, Elena Zotkina, Zhengping Jiang, Peter Bell, Kathleen McKeown

Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource Glossing (2024.emnlp-main)

Challenge:	Typical ASR systems segment input audio into utterances using purely acoustic information, which may not resemble sentence-like units expected by conventional machine translation systems for spoken language translation (SLT).
Approach:	They propose a model for correcting ASR acoustic segmentation using subtitles as a proxy dataset for creating synthetic aural utterances by modeling common error modes.
Outcome:	The proposed model improves performance on MT and audio-document cross-language information retrieval (CLIR) it uses subtitles as a proxy dataset to correct ASR acoustic segmentation .

Copied to clipboard

Changbing Yang, Garrett Nicolai, Miikka Silfverberg

Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations (2024.acl-long)

Challenge:	a paper addresses the data scarcity problem in automated glossing for low-resource languages . traditional manual documenting is laborintensive and a lack of data is limiting the accuracy of glossing .
Approach:	They propose to integrate token-level and sentence-level translations into models and integrate available dictionary resources into the model.
Outcome:	The proposed model improves word-level accuracy by 5% on the lowest-resource language Gitksan . the authors also show that the model improve on a simulated low-resourced language with fewer than 100 glossed sentences .

Copied to clipboard

Gregor Geigle, Radu Timofte, Goran Glavaš

The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation (2021.findings-emnlp)

Challenge:	Vision-and-language models with separate encoders for each modality are limited in availability.
Approach:	They propose a multilingual benchmark that offers (partial) translations of ImageNet labels to 100 languages, built without machine translation or manual annotation.
Outcome:	The proposed model outperforms models on English and low-resource languages.

Copied to clipboard

Orevaoghene Ahia, Julia Kreutzer, Sara Hooker

Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation (P19-1)

Challenge:	Extending state-of-the-art language models to low-resource languages requires addressing what we call the low-Resource double bind.
Approach:	They propose a low-resource double bind to refer to the co-occurrence of data limitations and compute resource constraints.
Outcome:	The proposed model improves performance on frequent sentences but disparates on infrequent ones.

Copied to clipboard

Nima Pourdamghani, Nada Aldarrab, Marjan Ghazvininejad, Kevin Knight, Jonathan May

Unsupervised Stem-based Cross-lingual Part-of-Speech Tagging for Morphologically Rich Low-Resource Languages (2022.naacl-main)

Challenge:	Using a dictionary, given a rough, target language natives can uncover the latent, fully-fluent rendering of the translation.
Approach:	They propose a method that breaks translation into two steps by generating a dictionary and then ‘translating’ the resulting pseudo-translation into a fully fluent translation.
Outcome:	The proposed method 'gets better translation results on high-resource languages than previously published unsupervised MT studies'

Copied to clipboard

Ramy Eskander, Cass Lowry, Sujay Khandagale, Judith Klavans, Maria Polinsky, Smaranda Muresan

Token-wise Curriculum Learning for Neural Machine Translation (2021.findings-emnlp)

Challenge:	Low-resource languages lack annotated data even for basic syntactic information such as parts of speech.
Approach:	They propose an unsupervised cross-lingual approach for POS tagging for low-resource languages of rich morphology . they further investigate morpheme-level alignment and projection and use of linguistic priors for morphological segmentation .
Outcome:	The proposed approach outperforms the word-based approach and outperfies word-driven approaches.

Copied to clipboard

Chen Liang, Haoming Jiang, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao, Tuo Zhao

ConLID: Supervised Contrastive Learning for Low-Resource Language Identification (2026.eacl-long)

Challenge:	Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of “easy” samples from training data at the early stage of training.
Approach:	They propose a token-wise curriculum learning approach that creates sufficient amounts of easy samples from training data.
Outcome:	The proposed approach outperforms baselines on five language pairs on low-resource languages.

Copied to clipboard

Negar Foroutan, Jakhongir Saydaliev, Grace Kim, Antoine Bosselut

BasqBBQ: A QA Benchmark for Assessing Social Biases in LLMs for Basque, a Low-Resource Language (2025.coling-main)

Challenge:	Low-resource languages and dialects remain difficult to identify and categorize accurately due to data in these languages and are limited to single-domain data.
Approach:	They propose a supervised contrastive learning approach to learn domain-invariant representations for low-resource languages by 3.2 percentage points while maintaining its performance for the high-resourced languages.
Outcome:	The proposed approach improves LID performance on out-of-domain data for low-resource languages by 3.2 percentage points while maintaining its performance for the high-resourced languages.

Copied to clipboard

Xabier Saralegi, Muitze Zulaika

Why should only High-Resource-Languages have all the fun? Pivot Based Evaluation in Low Resource Setting (2025.coling-main)

Challenge:	Existing pre-trained language models can propagate social biases in under-resourced languages like Basque.
Approach:	They propose a benchmark to assess biases in Basque using a multiple-choice question-answering task.
Outcome:	The proposed dataset is the first to assess biases in Basque across eight domains . larger models achieve better accuracy, but ambiguous cases remain challenging .

Copied to clipboard

Ananya Mukherjee, Saumitra Yadav, Manish Shrivastava

Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher (2020.findings-emnlp)

Challenge:	a limited number of evaluation metrics and resources are available for low-resource languages . a pivot-based evaluation framework is proposed to address these limitations .
Approach:	They propose a pivot-based evaluation framework that leverages advanced metrics for more meaningful evaluation.
Outcome:	The proposed framework extends the coverage of both lexical-based and embedding-based metrics even for languages not directly supported by advanced metrics.

Copied to clipboard

Giannis Karamanolakis, Daniel Hsu, Luis Gravano

Multi-Hall-SA: A Cross-lingual Benchmark for Multi-Type Hallucination Detection in Low-Resource South African Languages (2026.findings-eacl)

Challenge:	Existing approaches for transferring supervision across languages require expensive cross-lingual resources.
Approach:	They propose a cross-lingual teacher-student method that generates "weak" supervision in a target language using minimal cross-linguistic resources.
Outcome:	The proposed method outperforms state-of-the-art methods with a student classifier in 18 languages . it extracts and transfers only the most important task-specific seed words across languages based on translated seed words .

Copied to clipboard

Sello Ralethe, Jan Buys

Cross-lingual Multimodal Sentiment Analysis for Low-Resource Languages via Language Family Disentanglement and Rethinking Transfer (2025.findings-acl)

Challenge:	Large Language Models generate false or unsupported information, which can be difficult to detect in low-resource languages.
Approach:	They propose a cross-lingual benchmark for hallucination detection spanning English and South African languages.
Outcome:	The proposed model detects 23.6% fewer hallucinations in South African languages compared to English . human validation confirms the quality and cross-lingual alignment of the model .

Copied to clipboard

Long Chen, Shuoyu Guan, Xiaohua Huang, Wen-Jing Wang, Cai Xu, Ziyu Guan, Wei Zhao

VietMix: A Naturally-Occurring Parallel Corpus and Augmentation Framework for Vietnamese-English Code-Mixed Machine Translation (2026.eacl-long)

Challenge:	Existing multimodal sentiment analysis methods are limited to textual data and cannot handle multimodal scenarios.
Approach:	They propose a transfer learning framework that allows cross-lingual and cross-modal alignments and a language family disentanglement module that enhances the sharing of language universals within families.
Outcome:	The proposed method is superior to existing methods and can handle low-resource languages.

Copied to clipboard

Hieu Tran, Phuong-Anh Nguyen-Le, Huy Nghiem, Quang-Nhan Nguyen, Wei Ai, Marine Carpuat

Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi (2020.lrec-1)

Challenge:	Existing approaches to machine translation (MT) systems degrade when faced with code-mixed text.
Approach:	They propose a system that can augment Vietnamese-English code-mixed text with iterative fine-tuning and targeted filtering.
Outcome:	The proposed framework outperforms strong back-translation baselines and improves zero-shot models by up to +11.9 points.

Copied to clipboard

Devansh Mehta, Sebastin Santy, Ramaravind Kommiya Mothilal, Brij Mohan Lal Srivastava, Alok Sharma, Anurag Shukla, Vishnu Prasad, Venkanna U, Amit Sharma, Kalika Bali

Abstractive Summarization of Bengali Academic Videos Based on Audio Subtitles (2026.findings-eacl)

Challenge:	40% of all the languages in the world face the danger of extinction in the near future . when a language dies out, future generations lose a vital part of the culture that is necessary to completely understand it.
Approach:	They propose to use 4 technology-driven methods of data collection to collect data on Gondi, a low-resource vulnerable language spoken by 2.3 million tribal people in south and central India.
Outcome:	The proposed methods collected 12,000 translated words and/or sentences and identified more than 650 community members whose help can be solicited for future translation efforts.

Copied to clipboard

Lamisa Bintee Mizan Deya, Farhatun Shama, Abdul Aziz, Md Kaykobad Reza, Md Shahidul Salim

ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding (2025.findings-naacl)

Challenge:	Existing methods for summarizing educational videos in Bengali are limited due to the rapid growth of educational video content.
Approach:	They propose an end-to-end pipeline for the abstractive summarization of Bengali videos . they fine-tuned the BanglaT5 model on a new benchmark dataset .
Outcome:	The proposed system preprocesses audio and converts speech to text using Google's Speech Recognition API.

Copied to clipboard

Israel Abebe Azime, Atnafu Lambebo Tonja, Tadesse Destaw Belay, Yonas Chanie, Bontu Fufa Balcha, Negasi Haile Abadi, Henok Biadglign Ademtew, Mulubrhan Abebe Nerea, Debela Desalegn Yadeta, Derartu Dagne Geremew, Assefa Atsbiha Tesfu, Philipp Slusallek, Thamar Solorio, Dietrich Klakow

Visibility as Survival: Generalizing NLP for Native Alaskan Language Identification (2025.findings-acl)

Challenge:	Large language models (LLMs) evaluation is gaining increasing attention as they are typically trained on general-domain datasets while demonstrating notable performance on tasks out of their training domains.
Approach:	They propose an LLM evaluation benchmark for low-resource languages that focuses on low-rsource language understanding in culture-specific scenarios.
Outcome:	The proposed benchmarks outperform monolingual evaluations on proverb generation tasks and native language proverb descriptions on multiple choice tasks.

Copied to clipboard

Ivory Yang, Chunhui Zhang, Yuxin Wang, Zhongyu Ouyang, Soroush Vosoughi

Text Classification

Challenge:	Indigenous languages are largely invisible in commercial language identification systems, a stark reality exemplified by Google Translate’s LangID tool, which excludes all 150 Indigenous languages of North America.
Approach:	They propose a framework that shows how large language models and specialized classifiers can effectively identify these languages with minimal data.
Outcome:	The proposed framework shows that large language models and specialized classifiers can effectively identify these languages with minimal data.

Cross-Lingual Learning vs. Low-Resource Fine-Tuning: A Case Study with Fact-Checking in Turkish (2024.lrec-main)

Copied to clipboard

Recep Firat Cekinel, Çağrı Çöltekin, Pinar Karagoz

The State and Fate of Summarization Datasets: A Survey (2025.naacl-long)

Challenge:	Currently, most of the research on misinformation is focused on the English language . however, there is a scarcity of datasets for other languages, including Turkish .
Approach:	They propose a dataset that spans multiple domains and incorporates evidence from three Turkish fact-checking organizations.
Outcome:	The proposed dataset has the potential to advance research in the Turkish language.

Copied to clipboard

Noam Dahan, Gabriel Stanovsky

CaMEL: Case Marker Extraction without Labels (2022.acl-long)

Challenge:	Summarization is the task of shortening a text while preserving the most important information it contains.
Approach:	They propose a novel ontology covering sample properties, collection methods and distribution covering sample characteristics, collection method and distribution.
Outcome:	The proposed ontology covers sample properties, collection methods and distribution, and can be used to streamline future research into a more coherent body of work.

Copied to clipboard

Leonie Weissweiler, Valentin Hofmann, Masoud Jalili Sabet, Hinrich Schuetze

Persian Natural Language Inference: A Meta-learning Approach (2022.coling-1)

Challenge:	Existing models for morphological case marking and semantic content are not isomorphic.
Approach:	They propose a model that extracts case markers from a multilingual corpus using a noun phrase chunker and an alignment system.
Outcome:	The proposed model can extract case markers in 83 languages and visualise similarities and differences between case systems and annotate fine-grained deep cases in languages where they are not overtly marked.

Copied to clipboard

Heydar Soudani, Mohammad Hassan Mojab, Hamid Beigy

Cross-lingual Multi-Level Adversarial Transfer to Enhance Low-Resource Name Tagging (N19-1)

Challenge:	In general, shared representations are learned separately, either across tasks or across languages.
Approach:	They propose a meta-learning approach for inferring natural language in Persian . they use different task information or other language information to form additional high-quality tasks .
Outcome:	The proposed method outperforms the baseline approach, improving accuracy by roughly six percent.

Copied to clipboard

Lifu Huang, Heng Ji, Jonathan May

A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning (2022.coling-1)

Challenge:	Low-resource language name tagging is an important but challenging task.
Approach:	They propose a neural architecture that leverages multi-level adversarial transfer to improve name tagging for low-resource languages.
Outcome:	The proposed approach outperforms previous approaches on CoNLL data sets.

Copied to clipboard

Kunbo Ding, Weijie Liu, Yuejian Fang, Weiquan Mao, Zhe Zhao, Tao Zhu, Haoyan Liu, Rong Tian, Yiren Chen

WER We Stand: Benchmarking Urdu ASR Models (2025.coling-main)

Challenge:	Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries . however, its effect is limited by the gap between embedding clusters of different languages .
Approach:	They propose Embedding-Push, Attention-Pull, and Robust targets to transfer English embeddings to virtual multilingual embedders without semantic loss.
Outcome:	Experimental results show that the proposed method outperforms existing methods on cross-lingual tasks and can achieve a better multilingual alignment.

Copied to clipboard

Samee Arif, Aamina Jamal Khan, Mustafa Abbas, Agha Ali Raza, Awais Athar

Speech & Audio in NLP

Challenge:	This paper analyzes the performance of three ASR models for low-resource languages like Urdu . low-rural languages like urdu have significant gaps in accuracy and reliability .
Approach:	They evaluate the performance of three ASR models: Whisper, MMS, and Seamless-M4T . they present the first conversational speech dataset for benchmarking Urdu ASR systems .
Outcome:	The proposed model families outperform Whisper, MMS, and Seamless-M4T on two types of speech datasets.

Target-Oriented Relation Alignment for Cross-Lingual Stance Detection (2023.findings-acl)

Copied to clipboard

Ruike Zhang, Nan Xu, Hanxuan Yang, Yuan Tian, Wenji Mao

HIT - A Hierarchically Fused Deep Attention Network for Robust Code-mixed Language Representation (2021.findings-acl)

Challenge:	Existing work on cross-lingual stance detection has ignored the inconsistency in the occurrences and distributions of targets between languages, which consequently degrades the performance of stance detector in low-resource languages.
Approach:	They propose a fine-grained method which considers both target-level associations and language-level alignments to learn the in-language and cross-language associations.
Outcome:	The proposed method is compared with competing methods under variant settings and shows that it performs better in low-resource languages.

Copied to clipboard

Ayan Sengupta, Sourabh Kumar Bhattacharjee, Tanmoy Chakraborty, Md. Shad Akhtar

GlotLID: Language Identification for Low-Resource Languages (2023.findings-emnlp)

Challenge:	linguistics and morphology of resource-short code-mixed texts remain a key challenge in text processing.
Approach:	They propose a hierarchical transformer-based framework that captures the semantic relationship among words and hierarchically learns sentencelevel semantics using a fused attention mechanism.
Outcome:	The proposed framework improves on one European and five Indic languages on four NLP tasks on eleven datasets.

Copied to clipboard

Amir Kargaran, Ayyoob Imani, François Yvon, Hinrich Schuetze

Detecting Cybercrimes in Accordance with Pakistani Law: Dataset and Evaluation Using PLMs (2024.lrec-main)

Challenge:	Existing web-mined datasets for low-resource languages have been useful for low resource NLP.
Approach:	They propose a model that identifies 1665 low-resource languages and a new model that is rigorously evaluated and reliable.
Outcome:	The proposed model outperforms baselines when balancing F1 and false positive rate (FPR).

Copied to clipboard

Faizad Ullah, Ali Faheem, Ubaid Azam, Muhammad Sohaib Ayub, Faisal Kamiran, Asim Karim

Sinhala Encoder-only Language Models and Evaluation (2025.acl-long)

Challenge:	Roman Urdu is a widely used language in Pakistan but lacks sufficient resources and tools for text-based cybercrime detection.
Approach:	They propose to use a benchmark dataset for text-based cybercrime detection in Roman Urdu to improve the performance of pre-trained language models.
Outcome:	The proposed model achieves the highest performance on all metrics.

Copied to clipboard

Tharindu Ranasinghe, Hansi Hettiarachchi, Nadeesha Chathurangi Naradde Vidana Pathirana, Damith Premasiri, Lasitha Uyangodage, Isuri Nanomi Arachchige, Alistair Plum, Paul Rayson, Ruslan Mitkov

Tackling the Low-resource Challenge for Canonical Segmentation (2020.emnlp-main)

Challenge:	Recent advances in language models (LMs) have produced excellent results in many NLP tasks, but their effectiveness is highly dependent on available pre-training resources.
Approach:	They propose to collect the largest monolingual corpus for Sinhala and compile a benchmark and evaluate LMs on it.
Outcome:	The proposed language models outperform the popular multilingual LMs in downstream NLP tasks.

Copied to clipboard

Manuel Mager, Özlem Çetinoğlu, Katharina Kann

Generalists vs. Specialists: Evaluating Large Language Models for Urdu (2024.findings-emnlp)

Challenge:	morphological segmentation is a task of dividing words into their constituting morphemes . we compare two new approaches for the task when training data is limited .
Approach:	They propose to use an LSTM pointer-generator and a sequence-to-sequence model to perform canonical segmentation when training data is limited.
Outcome:	The proposed models outperform existing models on German, English, and Indonesian in low-resource scenarios by 11.4% accuracy.

Copied to clipboard

Samee Arif, Abdul Hameed Azeemi, Agha Ali Raza, Awais Athar

Cross-Lingual Sentence Compression for Length-Constrained Subtitles in Low-Resource Settings (2025.coling-main)

Challenge:	Urdu is underrepresented in natural language processing, yet it is underserved.
Approach:	They compare general-purpose models with special-purpose ones that have been fine-tuned on specific tasks.
Outcome:	The proposed models outperform general-purpose models on seven classification and seven generation tasks.

Copied to clipboard

Tollef Emil JÃ, rgensen, Ole Jakob Mengshoel

Comparing Prompt-Based and Standard Fine-Tuning for Urdu Text Classification (2023.findings-emnlp)

Challenge:	a new system for sentence compression is developed for broadcast and live media . the goal is to reduce the on-screen visual constraints of the text .
Approach:	They develop a machine translation and sentence compression system that trains on openly available parallel corpora organized by compression ratios.
Outcome:	The proposed system preserves high semantic meaning and metric evaluations for compressed contexts.

Copied to clipboard

Faizad Ullah, Ubaid Azam, Ali Faheem, Faisal Kamiran, Asim Karim

ManaTTS Persian: a recipe for creating TTS datasets for lower resource languages (2025.naacl-long)

Challenge:	Recent advances in natural language processing have demonstrated the efficacy of pre-trained language models for various downstream tasks.
Approach:	They compare prompt-based fine-tuning with standard fine-uning for text classification in Urdu and Roman Urdu languages.
Outcome:	The proposed approach improves up to 13% in accuracy in low-resource languages with limited labeled examples over standard fine-tuning approaches.

Copied to clipboard

Mahta Fetrat Qharabagh, Zahra Dehghanian, Hamid R. Rabiee

Speech & Audio in NLP

Challenge:	a new text-to-speech system is needed for visual impairments and the visually impaired . a text-based system is not available for all users, and is therefore limited to a limited audience.
Approach:	They propose to use ManaTTS, the most extensive publicly accessible Persian corpus . they use a fully transparent, MIT-licensed pipeline to collect transcribed speech datasets .
Outcome:	The proposed framework is the most extensive publicly accessible single-speaker Persian corpus . it includes tools for sentence tokenization, bounded audio segmentation, and forced alignment method .

Subword Segmental Language Modelling for Nguni Languages (2022.findings-emnlp)

Copied to clipboard

Francois Meyer, Jan Buys

Subword Evenness (SuE) as a Predictor of Cross-lingual Transfer to Low-resource Languages (2022.emnlp-main)

Challenge:	Subword segmentation is a standard practice in NLP, but is viewed as a preprocessing step for low-resource languages with complex morphologies.
Approach:	They propose a subword segmental language model that learns how to segment words while being trained for autoregressive language modelling.
Outcome:	The proposed model outperforms existing models on unsupervised morphological segmentation and outperfies standard subword segmenters on all 4 languages.

Copied to clipboard

Olga Pelloni, Anastassia Shaitarova, Tanja Samardzic

UniSent: Universal Adaptable Sentiment Lexica for 1000+ Languages (2020.lrec-1)

Challenge:	English is the most natural choice for cross-lingual transfer, but it is often not the best choice for low-resource languages.
Approach:	They propose to use pre-trained multilingual models to improve performance in low-resource languages via cross-lingual transfer.
Outcome:	The results show that languages written in non-Latin and non-alphabetic scripts are the best choices for improving performance on Masked Language Modelling tasks in a diverse set of 30 low-resource languages.

Copied to clipboard

Ehsaneddin Asgari, Fabienne Braune, Benjamin Roth, Christoph Ringlstetter, Mohammad Mofrad

Unlocking the Potential of Model Merging for Low-Resource Languages (2024.findings-emnlp)

Challenge:	Sentiment lexica are vital for sentiment analysis in absence of document-level annotations . linguistic resources are limited for at least a few hundred languages, putting them at risk of extinction .
Approach:	They introduce UniSent universal sentiment lexica for 1000+ languages . they use a Bible corpus to project sentiment information from English to other languages based on Twitter data .
Outcome:	The proposed method mitigates domain mismatch between Bible and Twitter by using embeddings . it compares to other sentiment seeding methods in a subset of languages with ground truth available .

Copied to clipboard

Mingxu Tao, Chen Zhang, Quzhe Huang, Tianyao Ma, Songfang Huang, Dongyan Zhao, Yansong Feng

Akan Cinematic Emotions (ACE): A Multimodal Multi-party Dataset for Emotion Recognition in Movie Dialogues (2025.findings-acl)

Challenge:	Adapting large language models (LLMs) to new languages requires continual pre-training followed by supervised fine-tuning.
Approach:	They propose a model merging solution that integrates LLMs with distinct capabilities into a single model without additional training.
Outcome:	The proposed model merging outperforms CT-then-SFT in low-resource languages with scarce data.

Copied to clipboard

David Sasu, Zehui Wu, Ziwei Gong, Run Chen, Pengyuan Shi, Lin Ai, Julia Hirschberg, Natalie Schluter

Sentiment Analysis

Challenge:	Akan Cinematic Emotions (AkaCE) is the first multimodal emotion dialogue dataset for an African language . it contains 385 emotion-labeled dialogues and 6162 utterances across audio, visual, and textual modalities, along with word-level prosodic prominence annotations.
Approach:	They propose to use AkaCE to analyze African cinematic emotions using word-level prosodic prominence annotations.
Outcome:	The Akan Cinematic Emotions (AkaCE) dataset addresses the significant lack of resources for low-resource languages in emotion recognition research.

Multilingual Dictionary Based Construction of Core Vocabulary (2020.lrec-1)

Copied to clipboard

Winston Wu, Garrett Nicolai, David Yarowsky

Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages (2022.acl-long)

Challenge:	Existing methods for core vocabulary lists for multiple applications are lacking coverage in sparse dictionaries . we propose a new method for definition and construction of core vocabulary sets based on coverage in dictionary dictionaria .
Approach:	They propose a functional definition and construction method for core vocabulary sets based on relative coverage of a target concept in bilingual dictionaries.
Outcome:	The proposed method achieves high overlap with existing vocabulary lists . it uses a cognate prediction method to recover missing coverage of the vocabulary .

Copied to clipboard

Wietse de Vries, Martijn Wieling, Malvina Nissim

VEEF-Multi-LLM: Effective Vocabulary Expansion and Parameter Efficient Finetuning Towards Multilingual Large Language Models (2025.coling-main)

Challenge:	Existing studies on cross-lingual generalisability of large pre-trained models use English training data and test data in unseen languages.
Approach:	They propose to use multilingual pre-trained models to model cross-lingual transfer in a selection of target languages.
Outcome:	The proposed model can be used to improve cross-lingual transfer performance in low-resource languages with no labeled training data.

Copied to clipboard

Jiu Sha, Mengxiao Zhu, Chong Feng, Yuming Shang

Towards Semi-Supervised Learning for Deep Semantic Role Labeling (D18-1)

Challenge:	Large Language Models (LLMs) have a significant disadvantage for low-resource languages . VEEF-Multi-LLM-8B excels in multilingual instruction-following tasks .
Approach:	They propose a low-resource multilingual large language model that expands the vocabulary for multilingual support.
Outcome:	The proposed model outperforms existing models in multilingual instruction-following tasks, but lags behind English-centric models in some tasks.

Copied to clipboard

Sanket Vaibhav Mehta, Jay Yoon Lee, Jaime Carbonell

LuxemBERT: Simple and Practical Data Augmentation in Language Model Pre-Training for Luxembourgish (2022.lrec-1)

Challenge:	Existing methods for semantic role labeling require an immense amount of semantic-role corpora and are therefore not suitable for low-resource languages or domains.
Approach:	They propose a semi-supervised method that outperforms the state-of-the-art on SRL . method explicitly enforcs syntactic constraints by augmenting the training objective with a syntastic-inconsistency loss component.
Outcome:	The proposed method outperforms the state-of-the-art on limited SRL training corpora on CoNLL-2012 English section.

Copied to clipboard

Cedric Lothritz, Bertrand Lebichot, Kevin Allix, Lisa Veiber, Tegawende Bissyande, Jacques Klein, Andrey Boytsov, Clément Lefebvre, Anne Goujon

Evaluating Performance of Pre-trained Word Embeddings on Assamese, a Low-resource Language (2024.lrec-main)

Challenge:	Pre-trained Language Models such as BERT are ubiquitous in NLP but are scarce for low-resource languages such as Luxembourgish.
Approach:	They propose a BERT model for Luxembourgish language that they use to augment pre-training datasets by partially translating text data from a closely related language.
Outcome:	The proposed model outperforms the baseline model and the mBERT model in Luxembourgish.

Copied to clipboard

Dhrubajyoti Pathak, Sukumar Nandi, Priyankoo Sarmah

Multilingual k-Nearest-Neighbor Machine Translation (2023.emnlp-main)

Challenge:	Word embeddings are not explored in high-resource languages such as Assamese, where resources are limited.
Approach:	They propose to use assamese pre-trained word embeddings for sequence labeling tasks such as Parts-of-speech and Named Entity Recognition to evaluate their performance.
Outcome:	The proposed embeddings outperform the existing methods on Parts-of-speech and Named Entity Recognition tasks.

Copied to clipboard

David Stap, Christof Monz

Event Extraction in Basque: Typologically Motivated Cross-Lingual Transfer-Learning Analysis (2024.lrec-main)

Challenge:	knearest-neighbor machine translation has shown remarkable improvements in machine translation quality by creating a datastore of cached examples.
Approach:	They combine k-nearest-neighbor machine translation with a datastore of cached examples to achieve significant improvements in machine translation quality.
Outcome:	The proposed approach improves translation quality by 5.3x in multilingual datastores, while limiting performance to low-resource languages.

Copied to clipboard

Mikel Zubillaga, Oscar Sainz, Ainara Estarrona, Oier Lopez de Lacalle, Eneko Agirre

Unsupervised Morphological Paradigm Completion (2020.acl-main)

Challenge:	Using a multilingual language model, Event Extraction tasks require humans to follow complicated guidelines and follow complicated rules.
Approach:	They propose a multilingual multilingual language model that is trained in a source language and applied to a target language.
Outcome:	The proposed model is based on a multilingual event extraction dataset for Basque . it shows that the shared linguistic characteristic between source and target languages does have an impact on transfer quality.

Copied to clipboard

Huiming Jin, Liwei Cai, Yihui Peng, Chen Xia, Arya McCarthy, Katharina Kann

CoNLL-UL: Universal Morphological Lattices for Universal Dependency Parsing (L18-1)

Challenge:	a task of generating morphological paradigms is a challenging unsupervised task for natural language processing systems . acuidados y acciones del idioma es a problem in linguistic annotators.
Approach:	They propose a task of unsupervised morphological paradigm completion using raw text and a lemma list.
Outcome:	The proposed system outperforms trivial baselines on 14 typologically diverse languages with ease and higher accuracy than minimally supervised systems.

Copied to clipboard

Amir More, Özlem Çetinoğlu, Çağrı Çöltekin, Nizar Habash, Benoît Sagot, Djamé Seddah, Dima Taji, Reut Tsarfaty

Exploring the Potential of Large Language Models (LLMs) for Low-resource Languages: A Study on Named-Entity Recognition (NER) and Part-Of-Speech (POS) Tagging for Nepali Language (2024.lrec-main)

Challenge:	Using the universal dependencies framework, we address the need for a universal representation of morphological analysis that can capture alternative morphology of surface tokens and is compatible with the segmentation and morphologic annotation guidelines prescribed for UD treebanks.
Approach:	They propose a new annotation format for word lattices that represent morphological analyses and a resource that obeys this format for a range of typologically different languages.
Outcome:	The proposed model can capture alternative morphological analyses of surface tokens and is compatible with the segmentation and morphology guidelines prescribed for UD treebanks.

Copied to clipboard

Bipesh Subedi, Sunil Regmi, Bal Krishna Bal, Praveen Acharya

MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer (2020.emnlp-main)

Challenge:	Large Language Models excel in various tasks like Named Entity Recognition and Part-of-Speech tagging.
Approach:	They propose to use large language models to perform NLP tasks such as Named Entity Recognition and Part-of-Speech tagging in Nepali.
Outcome:	The proposed models perform better than other approaches for Nepali NER and POS tagging tasks.

Copied to clipboard

Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych, Sebastian Ruder

Intriguing Properties of Compression on Multilingual Models (2022.emnlp-main)

Challenge:	Current deep pretrained models lack capacity to represent all languages . limited capacity is an issue even for high-resource languages where models are not included in training data at all.
Approach:	They propose an adapter-based framework that enables high portability and parameter-efficient transfer to arbitrary tasks and languages by learning modular language and task representations.
Outcome:	The proposed framework outperforms state-of-the-art models on cross-lingual transfer across languages and typologically diverse models.

Copied to clipboard

Kelechi Ogueji, Orevaoghene Ahia, Gbemileke Onilude, Sebastian Gehrmann, Sara Hooker, Julia Kreutzer

WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction (2023.acl-long)

Challenge:	Multilingual models are dependent on scaling to generalize to a growing number of languages . compression techniques can have disparate effects on model performance for low-resource languages if used sparsely .
Approach:	They propose to characterize the impact of sparsifying multilingual pre-trained language models during fine-tuning.
Outcome:	The proposed framework characterizes the impact of sparsifying multilingual pre-trained language models during fine-tuning.

Copied to clipboard

Qiyu Wu, Masaaki Nagata, Yoshimasa Tsuruoka

SHONGLAP: A Large Bengali Open-Domain Dialogue Corpus (2022.lrec-1)

Challenge:	Existing word alignment methods rely on manual data and lack generalization ability.
Approach:	They propose to use a weakly-supervised large-scale weakly supervised dataset for word alignment pre-training via span prediction to reduce the need for manual data.
Outcome:	The proposed method improves upon the best supervised baseline by 3.3 6.1 points in F1 and 1.5 6.1 point in AER.

Copied to clipboard

Syed Mostofa Monsur, Sakib Chowdhury, Md Shahrar Fatemi, Shafayat Ahmed

Dialogue Systems & Conversational Agents

Challenge:	Existing open-domain dialogue systems suffer from data scarcity due to unavailability of high-quality datasets for low-resource languages like Bengali.
Approach:	They propose to prepare large-scale open-domain dialogue datasets from podcasts and talk-shows and label them based on weak-supervision techniques.
Outcome:	The proposed corpus improves performance of large language models in case of downstream classification tasks during fine-tuning.

EmoInHindi: A Multi-label Emotion and Intensity Annotated Dataset in Hindi for Emotion Recognition in Dialogues (2022.lrec-1)

Copied to clipboard

Gopendra Vikram Singh, Priyanshu Priya, Mauajama Firdaus, Asif Ekbal, Pushpak Bhattacharyya

Natural Language Interfaces

Challenge:	Existing datasets for emotion recognition in dialogues are in English . existing datasets are limited to a few languages like Hindi .
Approach:	They propose a large conversational dataset in Hindi for multi-label emotion and intensity recognition in conversations . they use a Wizard-of-Oz manner to annotate dialogues with 16 emotion labels .
Outcome:	The proposed dataset contains 1,814 dialogues with 44,247 utterances in Hindi . it is based on a Wizard-of-Oz manner and can detect emotions in conversation .

TRANS-ZERO: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data (2025.findings-acl)

Copied to clipboard

Wei Zou, Sen Yang, Yu Bao, Shujian Huang, Jiajun Chen, Shanbo Cheng

TEMA: Token Embeddings Mapping for Enriching Low-Resource Language Models (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) have reshaped machine translation, but multilingual MT still relies heavily on parallel data for supervised fine-tuning.
Approach:	They propose a framework that leverages only monolingual data and the intrinsic multilingual knowledge of Large Language Models (LLMs).
Outcome:	The proposed framework matches models trained on large-scale parallel data and excels in non-English translation directions.

Copied to clipboard

Rodolfo Zevallos, Núria Bel, Mireia Farrús

Improving Low-Resource Machine Translation for Formosan Languages Using Bilingual Lexical Resources (2024.findings-acl)

Challenge:	Low-resource languages, that is, languages that do not have a massive amount of text, risk being almost excluded from the possibility of having good NLP applications.
Approach:	They propose an algorithm that maps token embeddings of a richly pre-trained model to a poorly trained model and creates a more complex model.
Outcome:	The proposed model reduces perplexity and is competitive or better for the most semantic tasks.

Copied to clipboard

Francis Zheng, Edison Marrese-Taylor, Yutaka Matsuo

Can LLMs Help Create Grammar?: Automating Grammar Creation for Endangered Languages with In-Context Learning (2025.coling-main)

Challenge:	Using bilingual lexicons for low-resource languages can improve machine translation for low resource languages.
Approach:	They propose to use bilingual lexicons to improve machine translation for low-resource languages . they use parallel data and bilingual dictionaries to generate pseudo-parallel sentences .
Outcome:	The proposed techniques improve translation between Mandarin and Formosan languages and Spanish and Nahuatl, a language pair consisting of languages from completely different language families.

Copied to clipboard

Piyapath T. Spencer, Nanthipat Kongborrirak

LexCLiPR: Cross-Lingual Paragraph Retrieval from Legal Judgments (2025.acl-long)

Challenge:	a new study examines the potential of large language models for documenting endangered languages . the model can be used to generate grammatical information for low-resource languages despite limitations .
Approach:	They examine the efficacy of LLMs in generating grammatical information for low-resource languages . they use bilingual dictionaries and parallel sentences of the unknown language as a case study .
Outcome:	The proposed model produces coherent grammatical rules and lexical entries using bilingual dictionaries and parallel sentences of the unknown language without building the model from scratch.

Copied to clipboard

Rohit Upadhya, Santosh T.y.s.s

IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation (2021.emnlp-main)

Challenge:	Existing work on IR focus on retrieving entire cases rather than precise, paragraph-level information.
Approach:	They propose a cross-lingual dataset for paragraph-level retrieval from ECtHR judgments . they evaluate retrieval models in a zero-shot setting and use multilingual case law guides .
Outcome:	The proposed model excels in cross-lingual retrieval, while siamese architectures are better suited for monolingual tasks.

Copied to clipboard

Samuel Cahyawijaya, Genta Indra Winata, Bryan Wilie, Karissa Vincentio, Xiaohong Li, Adhiguna Kuncoro, Sebastian Ruder, Zhi Yuan Lim, Syafri Bahar, Masayu Khodra, Ayu Purwarianti, Pascale Fung

Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in Kazakh (2025.acl-long)

Challenge:	Lack of publicly available NLG benchmarks for low-resource languages poses a challenge . authors show that IndoBART and IndoGPT achieve competitive performance on all tasks .
Approach:	They propose a benchmark to measure natural language generation progress in three low-resource languages of Indonesia . they use a corpus of pretraining datasets to build their models .
Outcome:	The proposed benchmark measures progress in Indonesian, Javanese, and Sundanese . the results highlight the importance of pretraining on closely related, localized languages .

Copied to clipboard

Nurkhan Laiyk, Daniil Orel, Rituraj Joshi, Maiya Goloburda, Yuxia Wang, Preslav Nakov, Fajri Koto

Quality Control for Crowdsourced Bilingual Dictionary in Low-Resource Languages (2022.lrec-1)

Challenge:	Instruction tuning in low-resource languages remains underexplored due to limited text data, particularly in government and cultural domains.
Approach:	They propose to open-source a large-scale instruction-following dataset covering key institutional and cultural knowledge relevant to Kazakhstan.
Outcome:	The proposed dataset improves LLMs’ understanding of procedural, legal, and structural governance topics.

Copied to clipboard

Hiroki Chida, Yohei Murakami, Mondheera Pituxcoosuvarn

An LLM-Enabled Knowledge Elicitation and Retrieval Framework for Zero-Shot Cross-Lingual Stance Identification (2024.findings-emnlp)

Challenge:	a recent study shows that crowdsourcing is becoming mainstream to create bilingual dictionaries . the number of people who can speak multiple low-resource languages is limited and the average ability of workers is low.
Approach:	They propose a method to aggregate the answers of evaluation tasks by majority voting . they use hyper questions to evaluate the reliability of workers and task-allocation method to select high-quality workers .
Outcome:	The proposed method improves quality of bilingual dictionaries by integrating answers by majority voting.

Copied to clipboard

Ruike Zhang, Yuan Tian, Penghui Wei, Daniel Zeng, Wenji Mao

Soft Gazetteers for Low-Resource Named Entity Recognition (2020.acl-main)

Challenge:	Existing research is conducted in monolingual setting on English datasets, whereas in other low-resource languages, it lacks sufficient data for training quality stance detection models.
Approach:	They propose a knowledge elicitation and retrieval framework that leverages the capability of large language models for stance knowledge acquisition and matches the target language input to the most relevant stance information.
Outcome:	The proposed framework improves on multilingual datasets and competitive baselines.

Copied to clipboard

Shruti Rijhwani, Shuyan Zhou, Graham Neubig, Jaime Carbonell

Named Entity Recognition

Challenge:	Existing named entity recognition models use gazetteers to improve performance, but they are limited in coverage and do not exist in low-resource languages.
Approach:	They propose a method that integrates Wikipedia information into named entity models by cross-lingual entity linking.
Outcome:	The proposed method improves on four low-resource languages with Wikipedia . it incorporates available information from english knowledge bases into neural models .

gaHealth: An English–Irish Bilingual Corpus of Health Data (2022.lrec-1)

Copied to clipboard

Séamus Lankford, Haithem Afli, Órla Ní Loinsigh, Andy Way

Zero-Shot Cross-Lingual NER Using Phonemic Representations for Low-Resource Languages (2024.emnlp-main)

Challenge:	Existing models for low-resource languages often focus on creating the largest possible dataset for generic translation.
Approach:	They develop a dataset for the specific domain of health for a low-resource English to Irish language pair and compare it to other similar datasets.
Outcome:	The proposed model improved BLEU score by 22.2 points compared with top performing models from the LoResMT2021 Shared Task.

Copied to clipboard

Jimin Sohn, Haeji Jung, Alex Cheng, Jooeon Kang, Yilin Du, David Mortensen

LuxEmbedder: A Cross-Lingual Approach to Enhanced Luxembourgish Sentence Embeddings (2025.coling-main)

Challenge:	Existing zero-shot cross-lingual NER approaches require substantial prior knowledge of the target language, which is impractical for low-resource languages.
Approach:	They propose a phonemic representation based on the International Phonetic Alphabet (IPA) to bridge the gap between representations of different languages.
Outcome:	The proposed method outperforms baseline models in low-resource languages with highest average F1 score and lowest standard deviation.

Copied to clipboard

Fred Philippy, Siwen Guo, Jacques Klein, Tegawende Bissyande

Representation Learning

Challenge:	Sentence embedding models are limited for many low-resource languages, including Luxembourgish.
Approach:	They propose to use Luxembourgish as an enhanced sentence embedding model with strong cross-lingual capabilities to address this issue.
Outcome:	The proposed model can embed Luxembourgish sentences better than high-resource languages.

Indic-TEDST: Datasets and Baselines for Low-Resource Speech to Text Translation (2024.lrec-main)

Copied to clipboard

Nivedita Sethiya, Saanvi Nair, Chandresh Maurya

Enhancing Cross-Lingual Transfer through Reversible Transliteration: A Huffman-Based Approach for Low-Resource Languages (2025.acl-long)

Challenge:	Speech-to-text Translation (ST) tasks are performed by human translators with proficiency in both the source and target languages.
Approach:	a new study compares the performance of SOTA ST models on low-resource languages . the authors propose to use a dataset to compare the models on high-resourced languages based on the results of their research .
Outcome:	a new study shows that only a few models have performed well on low-resource languages . the results indicate the need for specialized models for low- and high-resourced languages based on the dataset .

Copied to clipboard

Wenhao Zhuang, Yuan Sun, Xiaobing Zhao

Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models (2025.findings-acl)

Challenge:	Large language models demonstrate cross-lingual transfer capabilities, but these capabilities often fail to extend to low-resource languages, especially those utilizing non-Latin scripts.
Approach:	They propose to combine character transliteration with Huffman coding to create a complete transliterations framework that can be extended to other low-resource languages.
Outcome:	The proposed framework reduces storage requirements and improves accuracy and accuracy across multiple downstream tasks while maintaining performance on high-resource languages.

Copied to clipboard

Ahmed Elshabrawy, Thanh-Nhi Nguyen, Yeeun Kang, Lihan Feng, Annant Jain, Faadil Abdullah Shaikh, Jonibek Mansurov, Mohamed Fazli Mohamed Imam, Jesus-German Ortiz-Barajas, Rendi Chevi, Alham Fikri Aji

The Less the Merrier? Investigating Language Representation in Multilingual Models (2023.findings-emnlp)

Challenge:	Large Language Models excel in zero-shot and few-shot tasks, but their architecture makes them difficult to use.
Approach:	They adapt Large Language Models (LLMs) for zero-shot generalization using Statement Tuning . they find encoders can achieve zero- shot cross-lingual generalization .
Outcome:	The proposed model generalizes well across languages while being more efficient.

Copied to clipboard

Hellina Nigatu, Atnafu Tonja, Jugal Kalita

MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching (2025.findings-acl)

Challenge:	Multilingual models can be used to integrate multiple languages into one model and use cross-language transfer learning to improve performance for different NLP tasks.
Approach:	They propose to include languages in popular multilingual models and to use cross-language transfer learning to improve performance for different NLP tasks.
Outcome:	The proposed models perform better on downstream tasks for seen and unseen languages than community-centered models for low-resource languages.

Copied to clipboard

Fabian David Schmidt, Florian Schneider, Chris Biemann, Goran Glavaš

With Prejudice to None: A Few-Shot, Multilingual Transfer Learning Approach to Detect Social Bias in Low Resource Languages (2023.findings-acl)

Challenge:	Existing multilingual vision-language (VL) benchmarks typically only cover a handful of languages, underscoring the need for evaluation data for low-resource languages.
Approach:	They propose a multilingual vision-language benchmark that evaluates cross-modal and text-only topical matching across 205 languages.
Outcome:	The proposed model performs better in cross-modal and text-only topical matching in lower-resource languages than the most multilingual benchmarks.

Copied to clipboard

Nihar Sahoo, Niteesh Mallela, Pushpak Bhattacharyya

Killkan: The Automatic Speech Recognition Dataset for Kichwa with Morphosyntactic Information (2024.lrec-main)

Challenge:	Currently, the majority of social bias datasets available are in English and this inhibits progress on social bias detection in low-resource languages.
Approach:	They propose a dataset for social bias detection in Hindi and investigate multilingual transfer learning using publicly available English, Italian, and Korean datasets.
Outcome:	The proposed dataset is compared with a dataset available in English, Italian, and Korean using multilingual models.

Copied to clipboard

Chihiro Taguchi, Jefferson Saransig, Dayana Velásquez, David Chiang

Speech & Audio in NLP

Challenge:	Existing datasets for automatic speech recognition (ASR) in the endangered Kichwa language have been limited.
Approach:	They present Killkan, the first dataset for automatic speech recognition (ASR) in the Kichwa language, an indigenous language of Ecuador.
Outcome:	The proposed dataset shows that it can be used to build an automatic speech recognition system for the endangered language with reliable quality despite its small size.

Large Language Models for Multilingual Previously Fact-Checked Claim Detection (2025.findings-emnlp)

Copied to clipboard

Ivan Vykopal, Matúš Pikuliak, Simon Ostermann, Tatiana Anikina, Michal Gregor, Marian Simko

Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages (2023.findings-acl)

Challenge:	a new study evaluates large language models for multilingual previously fact-checked claim detection . authors assess seven LLMs across 20 languages in monolingual and cross-lingual settings .
Approach:	They evaluate large language models for multilingual previously fact-checked claim detection . they find they perform well for high-resource languages, struggle with low-resourced languages .
Outcome:	The proposed model performs well for high-resource languages, but struggle with low-resourced languages.

Copied to clipboard

Shivanshu Gupta, Yoshitomo Matsubara, Ankit Chadha, Alessandro Moschitti

SSP: Self-Supervised Prompting for Cross-Lingual Transfer to Low-Resource Languages using Large Language Models (2024.findings-emnlp)

Challenge:	Cross-Lingual Knowledge Distillation (CLKD) is a method to train AS2 models for low-resource languages without labeled data.
Approach:	They propose a method to train AS2 models for low-resource languages without labeled data . they use a translation-based WikiQA dataset and a multilingual AS2 dataset .
Outcome:	The proposed method outperforms or rivals fine-tuning with labeled data and machine translation and the teacher model.

Copied to clipboard

Vipul Rathore, Aniruddha Deb, Ankish Chandresh, Parag Singla, Mausam .

LexiVault: A Repository for Psycholinguistic Lexicons of Lesser-studied Languages (2024.lrec-main)

Challenge:	Recent studies have shown that very large language models (LLMs) can perform NLP tasks with just in-context learning (ICL) but their utility in other languages is underexplored.
Approach:	They propose a novel approach to in-context learning that uses noisy test data to generate more accurate labels for LLMs.
Outcome:	Experiments on three tasks and eleven LLMs show that the proposed approach outperforms existing in-context learning baselines on English NLP and reasoning tasks.

Copied to clipboard

Hind Saddiki, Samantha Wray, Daisy Li

Linguistics & Cognitive NLP

Challenge:	LexiVault is an open-source web tool with annotated lexicons and rich retrieval capabilities primarily developed for, but not restricted to, the support of psycholinguistic research .
Approach:	They propose to use LexiVault to design stimuli for low-resource languages with annotated lexicons and rich retrieval capabilities.
Outcome:	The LexiVault tool is designed to be user friendly and accommodate incremental growth of new and existing low-resource language lexicons in the system while abstracting programming complexity to foster more interest from the psycholinguistics community in exploring low-rsource languages.

Targeted Multilingual Adaptation for Low-resource Language Families (2024.findings-emnlp)

Copied to clipboard

C. Downey, Terra Blevins, Dhwani Serai, Dwija Parikh, Shane Steinert-Threlkeld

Towards a Deep Understanding of Multilingual End-to-End Speech Translation (2023.findings-emnlp)

Challenge:	Massively multilingual models are known to have limited utility in any one language, and to perform poorly on low-resource languages.
Approach:	They propose to adapt a pre-trained multilingual model to a language family and evaluate its performance on two downstream tasks and 11 evaluation languages.
Outcome:	The proposed model outperforms mono- and multilingual models on two downstream tasks and 11 evaluation languages.

Copied to clipboard

Haoran Sun, Xiaohu Zhao, Yikun Lei, Shaolin Zhu, Deyi Xiong

Multilingual Brain Surgeon: Large Language Models Can Be Compressed Leaving No Language behind (2024.lrec-main)

Challenge:	Recent years have witnessed the rapid development of end-to-end speech-totext translation (ST) which has demonstrated remarkable performance and outperformed conventional cascaded systems.
Approach:	They employ Singular Value Canonical Correlation Analysis to analyze representations learnt in a multilingual end-to-end speech translation model trained over 22 languages.
Outcome:	The proposed approach outperforms existing cascaded systems in predicting phonetic features and improves translation quality.

Copied to clipboard

Hongchuan Zeng, Hongshen Xu, Lu Chen, Kai Yu

Detecting Propaganda Techniques in Code-Switched Social Media Text (2023.emnlp-main)

Challenge:	Existing methods for MC focus on quantization and network pruning.
Approach:	They propose a calibration method that samples calibration data from various languages proportionally to the language distribution of the model training datasets.
Outcome:	The proposed method improves the performance of existing English-centric compression methods on the BLOOM multilingual LLM.

Copied to clipboard

Muhammad Salman, Asif Hanif, Shady Shehata, Preslav Nakov

MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP (2025.findings-acl)

Challenge:	a new study aims to detect propaganda in multiple languages using code-switching . social media platforms have made it easier for anyone to spread information to a wide audience .
Approach:	They propose to detect propaganda techniques in code-switched texts using a corpus of 1,030 texts . they propose to model multilinguality directly rather than using translation .
Outcome:	The proposed method combines different languages within the same text, presenting a challenge for automatic systems.

Copied to clipboard

Kurt Micallef, Claudia Borg

LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models (2026.acl-long)

Challenge:	Large Language Models (LLMs) have shown remarkable performance across various NLP tasks, largely due to their generalisability and ability to perform tasks without additional training.
Approach:	They evaluate the performance of 55 publicly available Large Language Models on Maltese, a low-resource language, using a newly introduced benchmark covering 11 discriminative and generative tasks.
Outcome:	The proposed models perform poorly on discriminative and generative tasks and smaller fine-tuned models perform better across all tasks.

Copied to clipboard

Jian Gao, Richeng Xuan, Zhaolu Kang, Dingshi Liao, Wenxin Huang, Zongmou Huang, Yangdi Xu, Bowen Qin, Zheqi He, Xi Yang, null Changjinli, Yonghua Lin

Error Analysis of Multilingual Language Models in Machine Translation: A Case Study of English-Amharic Translation (2024.emnlp-main)

Challenge:	Existing SEA-focused benchmarks miss Lao-specific cultural grounding and linguistic properties.
Approach:	They propose a multi-dimensional benchmark for assessing large language models in Lao . they use open-source and held-out subsets to evaluate languages with a hybrid pipeline .
Outcome:	LaoBench is the first large-scale, high-quality, and multidimensional benchmark for assessing LLM language understanding and reasoning in Lao.

Copied to clipboard

Hizkiel Alemayehu, Hamada Zahera, Axel-Cyrille Ngonga Ngomo

LegoMT2: Selective Asynchronous Sharded Data Parallel Training for Massive Neural Machine Translation (2025.findings-acl)

Challenge:	Multilingual large language models have significantly advanced machine translation, yet challenges remain for low-resource languages like Amharic.
Approach:	They evaluated the performance of NLLB-200 and M2M in English-Amharic bidirectional translation using the Lesan AI dataset.
Outcome:	The proposed models outperformed the existing models in English-Amharic bidirectional translation using the Lesan AI dataset.

Copied to clipboard

Fei Yuan, Yinquan Lu, Lei Li, Jingjing Xu

Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching (2025.findings-emnlp)

Challenge:	Existing methods to train a single model for massive languages have huge communication overheads and parameter interference.
Approach:	They propose an efficient training approach with an asymmetric multi-way model architecture for massive multilingual neural machine translation.
Outcome:	The proposed model is 16.2 faster than the distributed training method for M2M-100-12B while improving the translation performance by an average of 2.2 BLEU on Flores-101.

Copied to clipboard

Seoyeon Kim, Huiseo Kim, Chanjun Park, Jinyoung Yeo, Dongha Lee

SilverAlign: MT-Based Silver Data Algorithm for Evaluating Word Alignment (2024.lrec-main)

Challenge:	Recent large language models (LLMs) demonstrate multilingual abilities, yet they are English-centric due to dominance of English in training corpora.
Approach:	They propose to use a synthetic English-korean CS question-answering dataset to investigate this potential.
Outcome:	The proposed model can activate, identify and leverage knowledge for reasoning in low-resource languages.

Copied to clipboard

Abdullatif Koksal, Silvia Severini, Hinrich Schütze

Is linguistically-motivated data augmentation worth it? (2025.acl-long)

Challenge:	Word alignments are crucial for a variety of NLP tasks.
Approach:	They propose a method to automatically create silver data for evaluation of word aligners by exploiting machine translation and minimal pairs.
Outcome:	The proposed method correlates with gold benchmarks for 9 language pairs, making it a valid resource for evaluation of different languages and domains when gold data is not available.

Copied to clipboard

Ray Groshan, Michael Ginn, Alexis Palmer

Strengthening the WiC: New Polysemy Dataset in Hindi and Lack of Cross Lingual Transfer (2024.lrec-main)

Challenge:	Data augmentation is a widely-used technique for addressing data scarcity.
Approach:	They compare linguistically-motivated and linguisticly-naive data augmentation strategies for two low-resource languages with different morphological properties.
Outcome:	The proposed methods produce synthetic data that follows all linguistic constraints, but they require linguistic expertise and are more difficult to implement.

Copied to clipboard

Haim Dubossarsky, Farheen Dairkee

Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries (2025.findings-acl)

Challenge:	a new study addresses the problem of natural language processing in low-resource languages such as Hindi . the paper focuses on Word Sense Disambiguation, a fundamental NLP task that deals with polysemous words.
Approach:	They propose a Hindi WSD dataset that allows training and testing of contextualized models.
Outcome:	The proposed dataset enables training and testing of contextualized models in Hindi . the results show that the proposed dataset can handle polysemy tasks in low-resource languages .

Copied to clipboard

Haruki Sakajo, Yusuke Ide, Justin Vasselli, Yusuke Sakai, Yingtao Tian, Hidetaka Kamigaito, Taro Watanabe

Teaching Large Language Models to Translate on Low-resource Languages with Textbook Prompting (2024.lrec-main)

Challenge:	Existing approaches to cross-lingual vocabulary transfer face challenges when dealing with low-resource languages.
Approach:	They propose a dictionary-based crosslingual vocabulary transfer method that leverages bilingual dictionaries, which are available for many languages thanks to descriptive linguists.
Outcome:	The proposed method outperforms existing methods for low-resource languages.

Copied to clipboard

Ping Guo, Yubing Ren, Yue Hu, Yunpeng Li, Jiarui Zhang, Xingsheng Zhang, Heyan Huang

Low-Resource Languages LLM Disinformation is Within Reach: The Case of Walliserdeutsch (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have demonstrated impressive results in Machine Translation by following instructions, even without training on parallel data.
Approach:	They propose a Translate After LEarNing Textbook approach which aims to enhance LLMs’ ability to translate low-resource languages by learning from a textbook.
Outcome:	The proposed approach improves translation performance by 14.8% using 112 low-resource languages from FLORES-200 with two LLMs: ChatGPT and BLOOMZ.

Copied to clipboard

Andrei Kucharavy, Sherine Seppey, Cyril Vallez, Dimitri Percia David, Ljiljana Dolamic

Leveraging Loanword Constraints for Improving Machine Translation in a Low-Resource Multilingual Context (2025.emnlp-main)

Challenge:	a low-resource language lacks fluidity, but its capabilities can be leveraged.
Approach:	They investigate whether a moderately sophisticated attacker can perform an impersonation attack in the Walliserdeutsch dialect .
Outcome:	The proposed attack is performed in the Walliserdeutsch dialect, a low-resource language . the findings highlight the urgency of LLM detectability research in low-source languages.

Copied to clipboard

Felermino D. M. A. Ali, Henrique Lopes Cardoso, Rui Sousa-Silva

Scaling Low-Resource MT via Synthetic Data Generation with LLMs (2025.emnlp-main)

Challenge:	a recent study addresses the challenge of adapting loanwords during the translation process in low-resource languages.
Approach:	They propose a method that augments source sentences with loanword constraints . they then integrate loanwords as external linguistic knowledge into machine translation systems .
Outcome:	The proposed approach improves translation quality and handling loanword adaptation correctly in target languages.

Copied to clipboard

Ona de Gibert, Joseph Attieh, Teemu Vahtola, Mikko Aulamo, Zihao Li, Raúl Vázquez, Tiancheng Hu, Jörg Tiedemann

Topic Classification and Headline Generation for Maltese Using a Public News Corpus (2024.lrec-main)

Challenge:	a recent study has shown that LLM-generated synthetic data can improve low-resource machine translation performance . traditional data augmentation techniques like back-translation preserve the human-written target and synthesize the other .
Approach:	They construct a document-level synthetic corpus from English Europarl and extend it via pivoting to 147 additional language pairs.
Outcome:	The proposed model can significantly improve low-resource machine translation performance even when noisy.

Copied to clipboard

Amit Kumar Chaudhary, Kurt Micallef, Claudia Borg

Transferring BERT Capabilities from High-Resource to Low-Resource Languages Using Vocabulary Matching (2024.lrec-main)

Challenge:	Existing datasets for low-resource languages lack labelled data . public datasets only cover low-level syntactic tasks .
Approach:	They propose to use a news tag multi-label classification and a summary task by generating its title to generate a new semantic dataset for Maltese.
Outcome:	The proposed datasets show that current models lack the knowledge required to solve such tasks.

Copied to clipboard

Piotr Rybak

Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation (2024.lrec-main)

Challenge:	Pre-trained language models have revolutionized the natural language understanding landscape, but limited data hinders effective training of such models.
Approach:	They propose to transfer BERT capabilities from high-resource to low-resourced languages using vocabulary matching.
Outcome:	The proposed technique improves performance even when target language has minimal training data.

Copied to clipboard

Francois Meyer, Jan Buys

Human-Centered Supervision for Sentiment Analysis in Telugu: A Systematic Inquiry Beyond Accuracy (2026.findings-acl)

Challenge:	Existing data-to-text models are designed for the linguistic typology of English, but they are not suitable for low-resource languages.
Approach:	They propose a new dataset based on a subset of WebNLG that is agglutinative and low-resource data-to-text.
Outcome:	The proposed model outperforms existing models for isiXhosa and Finnish and fine-tunes machine translation models as the best method overall.

Copied to clipboard

Vallabhaneni Raj Kumar, Ashwin S, Supriya Manna, Niladri Sett, Cheedella V S N M S Hema Harshitha, Kurakula Harshitha, Basina Deepakraj, Anand Kumar Sharma, Tanuj Sarkar, Samanthapudi Shakeer, Bondada Navaneeth Krishna

Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque (2025.emnlp-main)

Challenge:	a limited amount of annotated data has slowed progress in machine learning for low-resource languages . a sentiment label records an annotator's final decision, but it is not a valid record of the annotation's interpretation.
Approach:	They propose a large-scale Telugu sentiment classification dataset annotated with sentiment labels and human-selected rationales from multiple native speakers.
Outcome:	The proposed model improves classification performance, explanation quality, and social bias by incorporating human rationales.

Copied to clipboard

Oscar Sainz, Naiara Perez, Julen Etxaniz, Joseba Fernandez de Landa, Itziar Aldabe, Iker García-Ferrero, Aimar Zabala, Ekhi Azurmendi, German Rigau, Eneko Agirre, Mikel Artetxe, Aitor Soroa

When Your Cousin Has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages (2024.lrec-main)

Challenge:	Instructing language models with user intent requires large instruction datasets limited to a limited set of languages.
Approach:	They propose to use existing LLMs and synthetically generated instructions to train models with user intent.
Outcome:	The proposed model outperforms base non-instructed models on Basque without Basque instructions.

Copied to clipboard

Niyati Bafna, Cristina España-Bonet, Josef van Genabith, Benoît Sagot, Rachel Bawden

UbuntuGuard: A Culturally-Grounded Policy Benchmark for Equitable AI Safety in African Languages. (2026.findings-acl)

Challenge:	Existing methods for unsupervised bilingual lexicon induction depend on good quality static or contextual embeddings for both languages.
Approach:	They propose a method for unsupervised bilingual lexicon induction between a related LRL and a high-resource language that only requires inference on a masked language model of the HRL.
Outcome:	The proposed method performs well on low-resource languages with 5M tokens against Hindi . it is compared with existing methods on (mid-resourced) Marathi and Nepali .

Copied to clipboard

Tassallah Abdullahi, Macton Mgonzo, Mardiyyah Oduwole, Paul Okewunmi, Abraham Toluwase Owodunni, Ritambhara Singh, Carsten Eickhoff

KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts (2025.emnlp-main)

Challenge:	Current guardian models are predominantly Western-centric and optimized for high-resource languages . low-resourced African languages are vulnerable to evolving harms, cross-lingual failures, cultural misalignment .
Approach:	They propose a policy-based safety benchmark for African languages built from adversarial queries authored by 155 domain experts across sensitive fields.
Outcome:	The proposed model overestimates multilingual safety, cross-lingual transfer provides partial but insufficient coverage, and dynamic models struggle to localize African-language contexts.

Copied to clipboard

Taebaek Hwang, Minseo Kim, Gisang Lee, Seonuk Kim, Hyunjun Eun

Trojsten Benchmark: Evaluating LLM Problem-Solving in Slovak STEM Competition Problems (2025.emnlp-main)

Challenge:	Understanding and reasoning over text within visual contexts poses a significant challenge for Vision-Language Models.
Approach:	They propose a benchmark for Korean Reading and rEasoning in Text-rich VQA Attuned to diverse visual contexts to address this challenge.
Outcome:	The proposed benchmark is tailored for Korean reading and rEasoning in text-rich VQA attuned to diverse visual contexts.

Copied to clipboard

Adam Zahradník, Marek Suppa

The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP (2026.acl-long)

Challenge:	Large language models have been used for grading open-ended responses and providing feedback beyond traditional methods.
Approach:	They propose a Slovak-language dataset and a rubric-based LLM grading framework . they quantify multistep reasoning performance by difficulty and show consistency under difficult items .
Outcome:	The proposed model outperforms existing models on Slovak-language competition problems . the model shows consistent underperformance on harder items and language sensitivity .

Copied to clipboard

Sheriff Issaka, Keyi Wang, Yinka Ajibola, Oluwatumininu Samuel-Ipaye, Zhaoyi Zhang, Nicte Aguillon Jimenez, Evans Kofi Agyei, Abraham Lin, Rohan Ramachandran, Sadick Abdul Mumin, Faith Nchifor, Mohammed Shuraim Issah, Erick Rosas Gonzalez, Lieqi Liu, Sylvester Kpei, Jemimah Kusi Osei, Carlene Ajeneza, Persis Boateng, Prisca Adwoa Dufie Yeboah, Saadia Gabriel

Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation Extraction (2026.acl-long)

Challenge:	Among the approximately 7,000 languages spoken globally, fewer than 20 receive substantial attention in NLP research.
Approach:	They propose to use African multi-modal speech and text data to validate African multimodal models and validate them on targeted language data.
Outcome:	The African Languages Lab's results show that the proposed model outperforms untrained models in 31 languages and a 1B-parameter model beats the commercial system in Yoruba and Twi.

Copied to clipboard

Vipul Kumar Rathore, Malik Hammad Faisal, Parag Singla, null Mausam