LOW-RESOURCE SETTING

Making a Point: Pointer-Generator Transformers for Disjoint Vocabularies (2020.aacl-srw)

Challenge:	Constrained decoding algorithms produce hypotheses satisfying all constraints, but they are computationally expensive and can lower the generated text quality.
Approach:	They propose a Mention Flag mechanism which traces whether lexical constraints are satisfied in outputs of an S2S decoder.
Outcome:	The proposed models maintain higher constraint satisfaction and text quality than baseline models and other constrained decoding algorithms.

Copied to clipboard

Nikhil Prabhu, Katharina Kann

A Little Pretraining Goes a Long Way: A Case Study on Dependency Parsing Task for Low-resource Morphologically Rich Languages (2021.eacl-srw)

Challenge:	Existing neural models rely on an overlap between source and target vocabularies to perform sequence-to-sequence tasks.
Approach:	They propose a pointer-generator transformer model for disjoint vocabularies that does not rely on an overlap between source and target vocs.
Outcome:	The proposed model outperforms a standard pointer-generator transformer by an average of 5.1 WER over 15 languages.

Copied to clipboard

Jivnesh Sandhan, Amrith Krishna, Ashim Gupta, Laxmidhar Behera, Pawan Goyal

Syntactic Text Processing

Challenge:	Neural dependency parsing has been a success for many domains and languages, but the bottleneck of massive labelled data limits its effectiveness for low resource languages.
Approach:	They propose to use morphological knowledge to improve dependency parsing for morphology rich languages in a low-resource setting to perform experiments.
Outcome:	The proposed method achieves an average gain of 2 points (UAS) and 3.6 points (LAS) on 10 MRLs in low-resource settings.

Neural Unsupervised Parsing Beyond English (D19-61)

Copied to clipboard

Katharina Kann, Anhad Mohananey, Samuel R. Bowman, Kyunghyun Cho

Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation (P19-1)

Challenge:	Unsupervised parsing is a task that can be learned without substantial prior knowledge.
Approach:	They train an unsupervised model for Arabic, Chinese, English, and German to learn syntactic structure from unlabeled text.
Outcome:	The PRPN architecture outperforms trivial baselines and acquires at least some parsing ability for all languages.

Copied to clipboard

Benjamin Heinzerling, Michael Strube

Semantic Text Processing

Challenge:	Pretrained contextual and non-contextual subword embeddings are available in over 250 languages, allowing massively multilingual NLP.
Approach:	They compare pretrained contextual and non-contextual subword embeddings with a contextual representation method, namely BERT, on multilingual named entity recognition and part-of-speech tagging.
Outcome:	The proposed method outperforms non-contextual embeddings on multilingual named entity recognition and part-of-speech tagging.

Towards Efficient Dialogue Processing in the Emergency Response Domain (2023.acl-srw)

Copied to clipboard

Tatiana Anikina

Dialogue Systems & Conversational Agents

Challenge:	Adapters perform dialogue act classification and domain-specific slot tagging in the emergency response domain.
Approach:	They propose to build a system that performs dialogue act classification and domain-specific slot tagging while being efficient, flexible and robust.
Outcome:	The proposed model performs well in the emergency response domain while being efficient, flexible and robust.

Compositional Representation of Morphologically-Rich Input for Neural Machine Translation (P18-2)

Copied to clipboard

Duygu Ataman, Marcello Federico

Improving Cross-lingual Transfer through Subtree-aware Word Reordering (2023.findings-emnlp)

Challenge:	Neural machine translation models are typically trained with fixed-size input and output vocabularies, which creates a bottleneck on their accuracy and generalization capability.
Approach:	They propose to replace the source-language embedding layer of NMT with a bi-directional recurrent neural network that generates compositional representations of the input at any desired level of granularity.
Outcome:	The proposed approach outperforms existing methods in a low-resource setting with five languages . the proposed approach consistently outperformed existing methods with a single word representation .

Copied to clipboard

Ofir Arviv, Dmitry Nikolaev, Taelin Karidi, Omri Abend

Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rust (2024.emnlp-industry)

Challenge:	Recent studies show that multilingual language models are not effective when dealing with less-represented languages.
Approach:	They propose a powerful reordering method that learns word-order patterns conditioned on the syntactic context from a small amount of annotated data.
Outcome:	The proposed method outperforms baselines on a variety of tasks and is effective in both zero-shot and few-shot scenarios.

Copied to clipboard

Vera Pavlova, Mohammed Makhlouf

Information Retrieval

Challenge:	Existing models that are pre-trained on a general domain can deteriorate performance due to domain shift when applied to new domains.
Approach:	They propose to train a multilingual non-profit IR system for the Islamic domain using Rust Language capabilities.
Outcome:	The proposed model outperforms models pre-trained on general domains and on resource-constrained devices.

One More Modality: Does Abstract Meaning Representation Benefit Visual Question Answering? (2025.findings-emnlp)

Copied to clipboard

Abhidip Bhattacharyya, Emma Markle, Shira Wein

Semantic Text Processing

Challenge:	incorporating explicit semantic information, in the form of Abstract Meaning Representation graphs, can enhance VQA models.
Approach:	They augment two vision-language models with sentence- and document-level AMRs . they find that in well-resourced settings, models are negatively impacted by AMR .
Outcome:	The proposed model improves in well-resourced and low-resource settings with AMR graphs . the model achieves 13.1% relative gain using sentence-level AMRs compared with the smaller model .

Generative Data Augmentation for Commonsense Reasoning (2020.findings-emnlp)

Copied to clipboard

Yiben Yang, Chaitanya Malaviya, Jared Fernandez, Swabha Swayamdipta, Ronan Le Bras, Ji-Ping Wang, Chandra Bhagavatula, Yejin Choi, Doug Downey

Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document (2023.findings-emnlp)

Challenge:	Recent advances in commonsense reasoning depend on large-scale human-authored training data.
Approach:	They propose a generative data augmentation technique that augments human-authored training data by using pretrained language models.
Outcome:	The proposed technique outperforms existing methods on commonsense reasoning benchmarks and enhances out-of-distribution generalization.

Copied to clipboard

Xiangnan Chen, Qian Xiao, Juncheng Li, Duo Dong, Jun Lin, Xiaozhong Liu, Siliang Tang

Extractive Summarization of Legal Decisions using Multi-task Learning and Maximal Marginal Relevance (2022.findings-emnlp)

Challenge:	Existing methods focus on manipulating entity features to find pairwise relations, yet neglect the more fundamental structural information that links disparate entity pairs together.
Approach:	They propose a Visual Relation Extraction framework that generates relation predictions on entity pairs extracted from scanned images and incorporates global structural knowledge into the representations of the entities.
Outcome:	The proposed framework outperforms existing methods in fine-tuning setting and yields stronger data-efficient performance in the low-resource setting.

Copied to clipboard

Abhishek Agarwal, Shanshan Xu, Matthias Grabmair

Better Character Language Modeling through Morphology (P19-1)

Challenge:	Summarizing legal decisions requires the expertise of law practitioners, which is time- and cost-intensive.
Approach:	They propose methods for extracting summarized legal decisions using limited expert annotated data.
Outcome:	The proposed models achieve ROUGE scores vis-à-vis expert extracted summaries that match inter-annotator comparisons.

Copied to clipboard

Terra Blevins, Luke Zettlemoyer

A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation (2021.emnlp-main)

Challenge:	Inflected words benefit more from explicitly modeling morphology than uninflectes . morphological supervision is also used to augment character language models in low-resource languages .
Approach:	They add morphological supervision to character language models via multitasking to improve BPC performance across 24 languages even when morphology data and language modeling data are disjointed.
Outcome:	The addition improves performance even when morphology data and language modeling data are disjointed.

Copied to clipboard

Shilei Liu, Xiaofeng Zhao, Bochao Li, Feiliang Ren, Longhui Zhang, Shujuan Yin

Dialogue Systems & Conversational Agents

Challenge:	Existing knowledge-grounded dialogues perform poorly when transfer into new domains with limited training samples.
Approach:	They propose a weakly supervised three-stage learning framework based on weakly-supervised learning based upon large scale ungrounded dialogues and unstructured knowledge base.
Outcome:	The proposed framework outperforms state-of-the-art methods even in zero-resource setting.

Phone Features Improve Speech Translation (2020.acl-main)

Copied to clipboard

Elizabeth Salesky, Alan W Black

Towards Summarizing Healthcare Questions in Low-Resource Setting (2022.coling-1)

Challenge:	End-to-end models for speech translation more tightly couple speech recognition (ASR) and machine translation (MT) compared to cascades, but performance gap remains in low-resource conditions .
Approach:	They propose two methods to incorporate phone features into current neural speech translation models.
Outcome:	The proposed models outperform existing models and cascades by up to 9 BLEU on low-resource conditions.

Copied to clipboard

Shweta Yadav, Cornelia Caragea

Normalizing Compositional Structures Across Graphbanks (2020.coling-main)

Challenge:	Existing methods to generate large-scale datasets are difficult in closed domains where human annotation requires domain expertise.
Approach:	They propose a method to generate diverse and semantic questions in a low-resource setting with the aim of summarizing healthcare questions.
Outcome:	The proposed method generates diverse, fluent, and informative summarized questions on healthcare question summarization datasets.

Copied to clipboard

Lucia Donatelli, Jonas Groschwitz, Matthias Lindemann, Alexander Koller, Pia Weißenhorn

Structured Data in NLP

Challenge:	Graph-based meaning representations (MRs) exhibit structural differences that reflect different theoretical and design considerations, presenting challenges to uniform linguistic analysis and cross-framework semantic parsing.
Approach:	They propose a method to normalize MRs at the compositional level by linguistically-grounded rules.
Outcome:	The proposed method increases the match in compositional structure between MRs and improves multi-task learning in a low-resource setting.

Translation via Annotation: A Computational Study of Translating Classical Chinese into Japanese (2026.eacl-long)

Copied to clipboard

Zilong Li, Jie Cao

Machine Translation

Challenge:	Ancient people translated classical Chinese into Japanese using a system of annotations placed around characters.
Approach:	They propose to introduce an LLM-based annotation pipeline and construct a dataset from digitized open-source translation data to improve sequence tagging tasks.
Outcome:	The proposed method achieves high scores on direct machine translation, but could serve as a supplement to LLMs to improve the quality of character’s annotation.

Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation (2025.findings-emnlp)

Copied to clipboard

Jan Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Maria Bielikova, Peter Brusilovsky

Low-Resource NLP

Challenge:	generative large language models are increasingly used for data augmentation tasks . text samples are mostly selected randomly and a comprehensive overview of other sample selection strategies is lacking.
Approach:	They compare random sample selection strategies and random sample sampling strategies to evaluate their effects in a low-resource setting.
Outcome:	The proposed model performance improvements are compared with other sample selection strategies.

Cross-language Sentence Selection via Data Augmentation and Rationale Training (2021.acl-long)

Copied to clipboard

Yanda Chen, Chris Kedzie, Suraj Nair, Petra Galuscakova, Rui Zhang, Douglas Oard, Kathleen McKeown

Self-supervised Graph Masking Pre-training for Graph-to-Text Generation (2022.emnlp-main)

Challenge:	a new approach to cross-language sentence selection is proposed for low-resource contexts . a cross-lingual embedding-based model is proposed that avoids translation entirely .
Approach:	They propose a cross-lingual embedding-based query relevance model that uses data augmentation and negative sampling techniques to directly learn a query-sentence pair.
Outcome:	The proposed approach performs better than state-of-the-art models on noisy parallel data . consistent improvements are seen across three language pairs over state- of-the art models .

Copied to clipboard

Jiuzhou Han, Ehsan Shareghi

CodePrompt: Task-Agnostic Prefix Tuning for Program and Language Generation (2023.findings-acl)

Challenge:	Large-scale pre-trained language models (PLMs) have advanced Graph-to-Text generation by processing the linearised version of a graph.
Approach:	They propose to mask pre-training tasks that neither require supervision signals nor adjust the architecture of the underlying pre-trained encoder-decoder model.
Outcome:	The proposed method achieves state-of-the-art results on WebNLG+2020 and EventNarrative datasets and is very efficient in the low-resource setting.

Copied to clipboard

YunSeok Choi, Jee-Hyong Lee

Automatic Readability Assessment for Closely Related Languages (2023.findings-acl)

Challenge:	Prompt-tuning methods have been used to solve inefficient parameter update and storage issues in Natural Language Generation tasks.
Approach:	They propose a task-agnostic prompt tuning method that reflects the traits of PLM for program language.
Outcome:	The proposed method is effective in three PLG tasks, not only in the full-data setting but also in the low-resource setting and cross-domain setting.

Copied to clipboard

Joseph Marvin Imperial, Ekaterina Kochmar

Mask-then-Fill: A Flexible and Effective Data Augmentation Framework for Event Extraction (2022.findings-emnlp)

Challenge:	In recent years, the main focus of research on automatic readability assessment (ARA) has shifted towards using expensive deep learning-based methods with the primary goal of increasing models’ accuracy.
Approach:	They focus on how linguistic aspects such as mutual intelligibility or degree of language relatedness can improve ARA in a low-resource setting.
Outcome:	The inclusion of CrossNGO, a novel feature exploiting n-gram overlap, significantly improves the performance of ARA models compared to the use of off-the-shelf large multilingual language models alone.

Copied to clipboard

Jun Gao, Changlong Yu, Wei Wang, Huan Zhao, Ruifeng Xu

Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment (2023.acl-long)

Challenge:	Existing data augmentation methods for event extraction are costly and time-consuming.
Approach:	They propose a data augmentation framework that randomly masks out an adjunct sentence fragment and infills a variable-length text span with a fine-tuned infilling model.
Outcome:	The proposed framework can generate more diverse data while keeping the original structure unchanged . it can replace a fragment of arbitrary length in the text with another fragment of variable length .

Copied to clipboard

Eshaan Tanwar, Subhabrata Dutta, Manish Borthakur, Tanmoy Chakraborty

Meta-Transfer Learning for Code-Switched Speech Recognition (2020.acl-main)

Challenge:	a handful of studies have explored ICL in a cross-lingual setting . emergence of large-scale, pretrained, Transformer-based language models has marked the commencement of an avant-garde era in NLP.
Approach:	They propose a novel prompt construction strategy to bridge the gap between ICL and cross-lingual text classification.
Outcome:	The proposed approach outperforms random prompt selection by a large margin across three tasks using 44 different cross-lingual pairs.

Copied to clipboard

Genta Indra Winata, Samuel Cahyawijaya, Zhaojiang Lin, Zihan Liu, Peng Xu, Pascale Fung

Multimodality

Challenge:	Increasing number of people in the world today speak a mixed-language as a result of being multilingual.
Approach:	They propose a method to transfer learn on a code-switched speech recognition system by extracting information from high-resource monolingual datasets.
Outcome:	The proposed model outperforms baselines on speech recognition and language modeling tasks and is faster to converge.

Effectiveness of Data Augmentation and Pretraining for Improving Neural Headline Generation in Low-Resource Settings (2022.lrec-1)

Copied to clipboard

Matej Martinc, Syrielle Montariol, Lidia Pivovarova, Elaine Zosa

Constrained Labeled Data Generation for Low-Resource Named Entity Recognition (2021.findings-acl)

Challenge:	Neural approaches for natural language generation (NLG) have mushroomed due to large textual resources.
Approach:	They propose to use a pretrained multilingual encoder-decoder model and a combination of two pretrained language models to train a model in a low-resource setting.
Outcome:	The proposed model outperforms the previous model on English and on a small subset of the same data.

Copied to clipboard

Ruohao Guo, Dan Roth

Data Augmentation for Context-Sensitive Neural Lemmatization Using Inflection Tables and Raw Text (N19-1)

Challenge:	Named Entity Recognition (NER) in lowresource languages has been a challenge for years . Existing methods suffer from low quality of annotated data in target language .
Approach:	They propose a method that uses projected annotations to generate pseudo supervised data with a transformer language model and a constrained beam search.
Outcome:	The proposed method achieves state-of-the-art or competitive performance in low-resource languages.

Copied to clipboard

Toms Bergmanis, Sharon Goldwater

Multimodality

Challenge:	Using context-sensitive approaches to lemmatization can improve accuracy on unseen and unseense words.
Approach:	They propose to use inflection tables and Wikipedia sentences to train a lemmatizer with little or no labeled corpus data to combine type-based learning with context.
Outcome:	The proposed model generalizes from unambiguous examples, improving overall and especially on unseen words.

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

Copied to clipboard

Manuel Mager, Özlem Çetinoğlu, Katharina Kann

ParaMac: A General Unsupervised Paraphrase Generation Framework Leveraging Semantic Constraints and Diversifying Mechanisms (2022.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

Jinxin Liu, Jiaxin Shi, Ji Qi, Lei Hou, Juanzi Li, Qi Tian

AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization (2021.naacl-main)

Challenge:	Existing unsupervised methods for paraphrase generation are weak in semantic equivalence or expression diversity.
Approach:	They propose a framework for unsupervised paraphrase generation that employs multi-aspect equivalence constraints and multi-granularity diversifying mechanisms to achieve good semantic equvalence and expressive diversity.
Outcome:	The proposed framework achieves 9.1% and 3.3% absolute gains over previous SOTA on Quora and MSCOCO and can improve to 18.0% and 4.6% on GLUE.

Copied to clipboard

Tiezheng Yu, Zihan Liu, Pascale Fung

Low-Resource NLP

Challenge:	State-of-the-art abstractive summarization models rely on extensive labeled data, which lowers their generalization ability on domains where such data are not available.
Approach:	They propose to use domain adaptation methods to simulate the low-resource domain adaptation setting for abstractive summarization systems with existing datasets across six diverse target domains.
Outcome:	The proposed model can be used to adapt to a low-resource domain adaptation setting.

Separating Context and Pattern: Learning Disentangled Sentence Representations for Low-Resource Extractive Summarization (2023.findings-acl)

Copied to clipboard

Ruifeng Yuan, Shichao Sun, Zili Wang, Ziqiang Cao, Wenjie Li

LVLM-Aware Multimodal Retrieval for RAG-Based Medical Diagnosis with General-Purpose Models (2026.findings-acl)

Challenge:	Context information is one of the key factors for extractive summarization, but other factors can be used to identify sentence importance.
Approach:	They propose to disentangle context and pattern factors for extractive summarization . they separate context and patterns for a better generalization ability in low-resource setting .
Outcome:	The proposed model can be used in the zero-shot setting or fine-tuned in the few-shot settings.

Copied to clipboard

Nir Mazor, Tom Hope

Multimodality

Challenge:	Using retrieval augmentation, large vision language models can be used for diagnostic accuracy, but multimodal retrieval-augmented diagnosis is challenging.
Approach:	They propose a lightweight mechanism for enhancing diagnostic performance of retrieval-augmented LVLMs by fine-tuning a multimodal retriever and general-purpose backbone models.
Outcome:	The proposed mechanism achieves competitive results without medical training compared to pre-trained models with extensive training.

Cross-Lingual Abstractive Summarization with Limited Parallel Resources (2021.acl-long)

Copied to clipboard

Yu Bai, Yang Gao, Heyan Huang

CASSI: Contextual and Semantic Structure-based Interpolation Augmentation for Low-Resource NER (2023.findings-emnlp)

Challenge:	Existing approaches to cross-lingual summarization use limited available cross-linguistic resources.
Approach:	They propose a multi-task framework for cross-lingual abstractive summarization that uses a single decoder to generate monolingual and cross-linguistic summaries.
Outcome:	Experiments on two CLS datasets show that the proposed model outperforms baseline models in low-resource and full-dataset scenarios.

Copied to clipboard

Tanmay Surana, Thi-Nga Ho, Kyaw Tun, Eng Siong Chng

Named Entity Recognition

Challenge:	Existing methods for text augmentation suffer from annotation corruption for token-level tasks like NER.
Approach:	They propose a novel augmentation scheme that generates high-quality contextually diverse augmentations while avoiding annotation corruption.
Outcome:	The proposed scheme outperforms existing methods at multiple low resource levels, in multiple languages, and for noisy and clean text.

Graph-Induced Transformers for Efficient Multi-Hop Question Answering (2022.emnlp-main)

Copied to clipboard

Giwon Hong, Jeonghwan Kim, Junmo Kang, Sung-Hyon Myaeng

Natural Language Interfaces

Challenge:	Recent MHQA tasks that require inter-paragraph/sentence linkages use graphs to model internal structural information within text.
Approach:	They propose a graph-induced transformer that applies graph-derived attention patterns directly into a PLM without external graph modules.
Outcome:	The proposed model can replace external graph modules while preserving model performance.

BanglaAbuseMeme: A Dataset for Bengali Abusive Meme Classification (2023.emnlp-main)

Copied to clipboard

Mithun Das, Animesh Mukherjee

Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback (2025.findings-emnlp)

Challenge:	a number of studies have tried to detect and control the spread of such abusive memes on social media platforms.
Approach:	They build a Bengali meme dataset to test models for abusive memes . they find that multimodal models that use both textual and visual information outperform unimodal models .
Outcome:	The proposed model outperforms unimodal models in a Bengali meme dataset.

Copied to clipboard

Chu Fei Luo, Samuel Dahan, Xiaodan Zhu