POS TAGGING

Evaluating zero-shot transfers and multilingual models for dependency parsing and POS tagging within the low-resource language family Tupían (2022.acl-srw)

Challenge:	PhoNLP is a multi-task learning model for joint Vietnamese part-of-speech (POS) tagging, named entity recognition (NER) and dependency parsing.
Approach:	They propose a multi-task learning model for Vietnamese part-of-speech tagging, named entity recognition and dependency parsing that fine-tunes the pre-trained Vietnamese language model PhoBERT for each task independently.
Outcome:	The proposed model outperforms a single-task learning approach that fine-tunes the pre-trained Vietnamese language model PhoBERT for each task independently.

Copied to clipboard

Frederic Blum

Building Hierarchically Disentangled Language Models for Text Generation with Named Entities (2020.coling-main)

Challenge:	Existing studies on NLP applications for low-resource languages have not been done in this area.
Approach:	They propose to replicate the transferability of dependency parsers and POS taggers trained on closely related languages within the low-resource language family Tupan.
Outcome:	The proposed models replicate the transferability of dependency parsers and POS taggers trained on closely related languages within the low-resource language family Tupan.

Copied to clipboard

Yash Agarwal, Devansh Batra, Ganesh Bagler

NLP Tools for Predictive Maintenance Records in MaintNet (2020.aacl-demo)

Challenge:	Named entities pose a unique challenge to traditional methods of language modeling.
Approach:	They propose a Hierarchically Disentangled Model for named entities in cooking recipes using a dataset from several publicly available online sources.
Outcome:	The proposed model is based on 158,473 cooking recipes from public sources.

Copied to clipboard

Farhad Akhbardeh, Travis Desell, Marcos Zampieri

Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization (2023.tacl-1)

Challenge:	Maintenance logbooks often contain free text fields with domain specific terms, abbreviations, and non-standard spelling . most standard NLP pipelines for pre-processing and annotation are trained on standard contemporary corpora.
Approach:	They propose to create an open-source library and data repository for predictive maintenance language datasets and to evaluate the tools available at MaintNet.
Outcome:	The proposed tools improve the performance of existing pipelines and improve the quality of the existing ones.

Copied to clipboard

Thomas Effland, Michael Collins

ZAEBUC: An Annotated Arabic-English Bilingual Writer Corpus (2022.lrec-1)

Challenge:	Existing methods for cross-lingual syntactic analysis have been shown to be effective for low-resource languages.
Approach:	They propose to use low-order statistical functions to shape model distributions for semi-supervised learning on low-resource datasets.
Outcome:	The proposed method improves POS and LAS on 5 target languages and provides significant gains over strong cross-lingual-transfer-plus-fine-tuning baselines for modest amounts of label data.

Copied to clipboard

Nizar Habash, David Palfreyman

Handling Normalization Issues for Part-of-Speech Tagging of Online Conversational Text (L18-1)

Challenge:	ZAEBUC is an annotated Arabic-English bilingual writer corpus . it is a corpus of short essays written by first-year university students .
Approach:	They propose to use a standard Arabic-English bilingual writer corpus to match comparable texts written by the same writer on different occasions.
Outcome:	The ZAEBUC corpus is an annotated Arabic-English bilingual writer corpus by first-year university students at Zayed University in the United Arab Emirates.

Copied to clipboard

Géraldine Damnati, Jeremy Auguste, Alexis Nasr, Delphine Charlet, Johannes Heinecke, Frédéric Béchet

Dialogue Systems & Conversational Agents

Challenge:	a new approach to POS tagging noisy user generated text is proposed . word embeddings are trained on a noisy corpus to address both normalization and POS.
Approach:	They propose to use word embeddings to normalize text before tagging it, while a gated neural network based tagger handles the remaining errors.
Outcome:	The proposed approach normalizes some errors before tagging, while a gated neural network handles the remaining errors.

Towards Unsupervised Morphological Analysis of Polysynthetic Languages (2022.aacl-short)

Copied to clipboard

Sujay Khandagale, Yoann Léveillé, Samuel Miller, Derek Pham, Ramy Eskander, Cass Lowry, Richard Compton, Judith Klavans, Maria Polinsky, Smaranda Muresan

BanSuite: A Unified Toolkit and Software Platform for Low-Resource NLP in Bangla (2026.eacl-demo)

Challenge:	Polysynthetic languages are low-resource, lacking large scale annotated datasets needed to build and/or evaluate computational models.
Approach:	They propose to use linguistic priors to help with morphological segmentation and part-of-speech tagging tasks for Adyghe and Inuktitut .
Outcome:	The proposed methods improve morphological segmentation and part-of-speech tagging tasks on Adyghe and Inuktitut.

Copied to clipboard

Md. Abu Sayed, Faisal Ahamed Khan, Jannatul Ferdous Tuli, Nabeel Mohammed, Mohammad Ruhul Amin, Mohammad Mamun Or Rashid

Cross-Genre Learning for Old English Poetry POS Tagging (2025.acl-srw)

Challenge:	Existing efforts to improve Bangla's NLP performance have focused on isolated tasks such as Part-of-Speech tagging and Named Entity Recognition (NER) but comprehensive, integrated systems for core NLP tasks such Shallow Parsing and Dependency Parser are largely absent.
Approach:	They propose to integrate a large-scale, manually annotated Bangla Treebank with high-quality pretrained models for POS tagging, NER, shallow parsing, and dependency parse.
Outcome:	The proposed system achieves strong in-domain baseline performance while maintaining high efficiency in resource usage.

Copied to clipboard

Irene Miani, Sara Stymne, Gregory R. Darwin

Dependency Parsing with Backtracking using Deep Reinforcement Learning (2022.tacl-1)

Challenge:	a recent study highlights the linguistic differences between Old English poetry and prose . linguistic analysis tools struggle to address these differences, says a researcher .
Approach:	They analyze annotated corpora representing each genre to find similarities between poetry and prose . they find that there are several types of structural differences between the two genres .
Outcome:	The results show that integrating small amounts of target data improves prediction accuracy compared to excluding it entirely.

Copied to clipboard

Franck Dary, Maxime Petit, Alexis Nasr

PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding (2020.findings-emnlp)

Challenge:	Greedy algorithms for NLP such as transition-based parsing are prone to error propagation.
Approach:	They propose to allow transition-based parsing to backtrack in cases where evidence contradicts the current solution.
Outcome:	The proposed behavior can be implemented on POS tagging and dependency parsing . it shows that backtracking is an effective means to fight error propagation .

Copied to clipboard

Zhao Jinman, Shawn Zhong, Xiaomin Zhang, Yingyu Liang

I Speak for the Árboles: Developing a Dependency Treebank for Spanish L2 and Heritage Speakers (2025.acl-srw)

Challenge:	Existing word embeddings assume fixed finite-size vocabularies, hindering their ability to provide useful word representations for out-of-vocaulary words.
Approach:	They propose a model that generalizes word embeddings without extra contextual information . they use the spellings of words to model subword segmentation and compute subword-based compositional word embeds.
Outcome:	The proposed model can generate meaningful subword segmentations without any source of explicit morphological knowledge.

Copied to clipboard

Emiliana Pulido, Robert Pugh, Zoey Liu

Self-Training Pre-Trained Language Models for Zero- and Few-Shot Multi-Dialectal Arabic Sequence Labeling (2021.eacl-main)

Challenge:	Existing dependency treebanks for learner writing are limited due to morphosyntactic features.
Approach:	They propose to use a dependency treebank for Spanish learner writing from the UC Davis COWSL2H corpus to incorporate lemmatization, POS tagging, and syntactic dependencies.
Outcome:	The proposed treebanks are openly accessible to motivate future development of learner-oriented language technologies.

Copied to clipboard

Muhammad Khalifa, Muhammad Abdul-Mageed, Khaled Shaalan

Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT (D19-1)

Challenge:	Existing approaches to fine-tune pre-trained language models for downstream tasks require labeled data.
Approach:	They propose to self-train pre-trained language models to improve performance on data-scarce varieties by as large as 10% F1 and 2% accuracy.
Outcome:	The proposed model improves zero-shot MSA-to-DA transfer by as large as 10% F1 (NER) and 2% accuracy (POS tagging).

Copied to clipboard

Shijie Wu, Mark Dredze

”Diversity and Uncertainty in Moderation” are the Key to Data Selection for Multilingual Few-shot Transfer (2022.findings-naacl)

Challenge:	Pretrained contextual representation models have pushed forward the state-of-the-art on many NLP tasks.
Approach:	They propose to use a model that is pretrained on 104 languages for cross-lingual transfer.
Outcome:	The proposed model performs well on 5 NLP tasks covering 39 languages from various language families.

Copied to clipboard

Shanu Kumar, Sandipan Dandapat, Monojit Choudhury

Semi-Supervised Semantic Role Labeling with Cross-View Training (D19-1)

Challenge:	Existing approaches for few-shot transfer show significant gain over zero-shot transfers . language resource distribution is skewed across the world's languages . proposed methods use multiple measures such as data entropy and gradient embedding .
Approach:	They propose a loss embedding method for sequence labeling tasks that induces diversity and uncertainty sampling similar to gradient embeddment.
Outcome:	The proposed methods outperform baseline methods for POS tagging, NER, and NLI tasks for up to 20 languages.

Copied to clipboard

Rui Cai, Mirella Lapata

Building a User-Generated Content North-African Arabizi Treebank: Tackling Hell (2020.acl-main)

Challenge:	Recent approaches rely on expensive annotations and are unavailable in low resource scenarios (e.g., rare languages or domains).
Approach:	They propose an end-to-end SRL model which leverages unlabeled data and propose to reduce the annotation effort involved via semi-supervised learning.
Outcome:	The proposed model outperforms the state-of-the-art in English and consistently improves performance in other languages, including Chinese, German, and Spanish.

Copied to clipboard

Djamé Seddah, Farah Essaidi, Amal Fethi, Matthieu Futeral, Benjamin Muller, Pedro Javier Ortiz Suárez, Benoît Sagot, Abhishek Srivastava

End-to-End Graph-Based TAG Parsing with Neural Networks (N18-1)

Challenge:	a treebank for a north-African Arabic dialect known for code-switching is made freely available . authors: geopolitical events are a factor highlighting a language deficiency in terms of natural language processing resources .
Approach:	They propose to make a treebank for a romanized user-generated content variety of Algerian . they supplement it with 50k unlabeled sentences from common crawl and web-crawled data .
Outcome:	The proposed treebank is made of 1500 sentences, fully annotated in morpho-syntax and universal dependency syntax, with full translation at both the word and sentence levels.

Copied to clipboard

Jungo Kasai, Robert Frank, Pauli Xu, William Merrill, Owen Rambow

Multimodality

Challenge:	Using BiLSTMs, highway connections, and character-level CNNs, we propose a graph-based Tree Adjoining Grammar (TAG) parser.
Approach:	They propose a graph-based Tree Adjoining Grammar parser that uses BiLSTMs, highway connections, and character-level CNNs.
Outcome:	The proposed parser outperforms the previously reported best by more than 2.2 LAS and UAS points.

EnerGIZAr: Leveraging GIZA++ for Effective Tokenizer Initialization (2025.findings-acl)

Copied to clipboard

Pranaydeep Singh, Eneko Agirre, Gorka Azkune, Orphee De Clercq, Els Lefever

Korean Morphological Analysis with Tied Sequence-to-Sequence Multi-Task Model (D19-1)

Challenge:	Continual pre-training has long been considered the default strategy for adapting models to non-English languages, but struggles with initializing new embeddings, especially for non-Latin scripts.
Approach:	They propose a method that leverages statistical word alignment techniques to improve continual pre-training by leveraging word alignment matrix between source and target tokens.
Outcome:	The proposed method outperforms existing methods on key NLP tasks including POS tagging, Sentiment Analysis, NLI, and NER in Hindi, Basque, Arabic and Korean.

Copied to clipboard

Hyun-Je Song, Seong-Bae Park

An Empirical Exploration of Local Ordering Pre-training for Structured Prediction (2020.findings-emnlp)

Challenge:	Korean morphological analysis is a sequence of morpheme processing and POS tagging.
Approach:	They propose a tied sequence-to-sequence multi-task model for training the two tasks simultaneously without any explicit regularization.
Outcome:	The proposed model achieves state-of-the-art performance without any explicit regularization.

Copied to clipboard

Zhisong Zhang, Xiang Kong, Lori Levin, Eduard Hovy

ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks (2024.eacl-long)

Challenge:	Recent studies have shown that pre-training contextualized encoders with language model objectives is effective for structured prediction.
Approach:	They propose a semi-supervised method for pre-training contextualized encoders with language model objectives.
Outcome:	The proposed method is effective on three typical structured prediction tasks in four languages.

Copied to clipboard

Bolei Ma, Ercong Nie, Shuzhou Yuan, Helmut Schmid, Michael Färber, Frauke Kreuter, Hinrich Schuetze

The Secret is in the Spectra: Predicting Cross-lingual Task Performance with Spectral Similarity Measures (2020.emnlp-main)

Challenge:	Prompt-based methods have been successfully applied to multilingual pretrained language models for zero-shot cross-lingual understanding.
Approach:	They propose a prompt-based method for token-level sequence labeling tasks . they propose to decompose an input sentence into single tokens and apply one prompt template to each token.
Outcome:	The proposed method outperforms Vanilla fine-tuning and Prompt-Tuning in zero-shot cross-lingual transfer . the method also attains state-of-the-art performance when employed with the mT5 model .

Copied to clipboard

Haim Dubossarsky, Ivan Vulić, Roi Reichart, Anna Korhonen

Representation Learning

Challenge:	Existing studies have suggested that bilingual lexicon induction is influenced by the (dis)similarity of the languages at hand.
Approach:	They propose to measure the isomorphism of monolingual embedding spaces based on their spectra and introduce isometric measures to measure their similarity.
Outcome:	The proposed measures outperform standard isomorphism measures while being more tractable and easier to interpret.

Joint Chinese Word Segmentation and Part-of-speech Tagging via Multi-channel Attention of Character N-grams (2020.coling-main)

Copied to clipboard

Yuanhe Tian, Yan Song, Fei Xia

Subword Pooling Makes a Difference (2021.eacl-main)

Challenge:	Chinese word segmentation and part-of-speech tagging can be performed in a sequential order . existing studies have shown that jointly performing them can be effective .
Approach:	They propose a character-based neural model enhanced by multi-channel attention of n-grams.
Outcome:	The proposed model outperforms baseline models on five benchmark datasets.

Copied to clipboard

Judit Ács, Ákos Kádár, Andras Kornai

Lexical Normalization for Code-switched Data and its Effect on POS Tagging (2021.eacl-main)

Challenge:	Contextual word-representations use subword tokenization to handle large vocabularies and unknown words.
Approach:	They propose to use the first subword for morphological probing, POS tagging and NER to pool multiple subwords that correspond to a single word in contextual language models.
Outcome:	The proposed model outperforms two multilingual models on morphological probing, POS tagging and NER tasks in 9 languages.

Copied to clipboard

Rob van der Goot, Özlem Çetinoğlu

To Annotate or Not? Predicting Performance Drop under Domain Shift (D19-1)

Challenge:	Social media data can be used to improve natural language processing performance, but it is often overlooked by lexical normalization systems.
Approach:	They propose three lexical normalization models specifically designed to handle code-switched data and evaluate their performance on POS tags.
Outcome:	The proposed models outperform monolingual models and lead to 5.4% performance increase for POS tagging compared to unnormalized input.

Copied to clipboard

Hady Elsahar, Matthias Gallé

Information Extraction & Text Mining

Challenge:	Performance drop due to domain-shift is an endemic problem for NLP models in production.
Approach:	They propose to use H-divergence, reverse classification accuracy and confidence measures to predict performance drop under domain-shift without any target domain labels.
Outcome:	The proposed method predicts performance drops with an error rate as low as 2.15% and 0.89% for sentiment analysis and POS tagging respectively.

Evaluating morphological typology in zero-shot cross-lingual transfer (2021.acl-long)

Copied to clipboard

Antonio Martínez-García, Toni Badia, Jeremy Barnes

Grouping Words with Semantic Diversity (2021.naacl-main)

Challenge:	morphological typology has been used to improve cross-lingual transfer . however, some language families and typologies consistently perform worse .
Approach:	They examine effects of morphological typology on zero-shot cross-lingual transfer . they perform part-of-speech tagging and sentiment analysis on 19 languages .
Outcome:	The proposed model improves on fusional and introflexive languages, but some language families and typologies perform worse.

Copied to clipboard

Karine Chubarian, Abdul Rafae Khan, Anastasios Sidiropoulos, Jia Xu

Challenge:	a new approach to grouping input words based on their semantic diversity is proposed . high-dimensional inputs and learning complexity hinders deep learning generalization, authors say .
Approach:	They propose a way to group input words based on their semantic diversity to simplify input language representation with low ambiguity.
Outcome:	The proposed methods generalize NLP models and demonstrate improvements on medium-scale machine translation tasks.

Character-Level Feature Extraction with Densely Connected Networks (C18-1)

Copied to clipboard

Chanhee Lee, Young-Bum Kim, Dongyub Lee, Heuiseok Lim

Information Extraction & Text Mining

Challenge:	Existing methods to generate character-level features with neural architectures such as CNN or Recurrent Neural Network (RNN) are slow and generate position-independent features.
Approach:	They propose a method that uses a densely connected network to extract character-level features from words using CNN and RNN.
Outcome:	The proposed method shows robustness and effectiveness while being faster than CNN- or RNN-based methods.

Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging (D18-1)

Copied to clipboard

Tao Gui, Qi Zhang, Jingjing Gong, Minlong Peng, Di Liang, Keyu Ding, Xuanjing Huang

A Fine-Grained Domain Adaption Model for Joint Word Segmentation and POS Tagging (2021.emnlp-main)

Challenge:	Existing POS tagging methods for Twitter use labeled newswire text . however, Twitter users tend to mimic formal media expressions and develop linguistically informal styles.
Approach:	They propose to use newswire text to learn POS tagging for Twitter while twitter users are developing linguistically informal styles.
Outcome:	The proposed method achieves better performance than state-of-the-art methods on three different datasets.

Copied to clipboard

Peijie Jiang, Dingkun Long, Yueheng Sun, Meishan Zhang, Guangwei Xu, Pengjun Xie

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

Challenge:	Experimental results show that joint models of word segmentation and POS tagging can lead to better performance because they are closely related.
Approach:	They propose a domain adaption method for Chinese word segmentation and POS tagging that uses a simple metric to model the gaps between target and target domains.
Outcome:	The proposed method can gain significant performance improvements over baselines on a benchmark dataset.

Copied to clipboard

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

Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections (P19-1)

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

Junxian He, Zhisong Zhang, Taylor Berg-Kirkpatrick, Graham Neubig

ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing (2023.emnlp-main)

Challenge:	Current systems for syntactic analysis tasks rely heavily on large scale annotated data.
Approach:	They propose to learn a generative model with a structured prior that uses labeled source and unlabeled target data jointly.
Outcome:	The proposed model improves on part-of-speech tagging and dependency parsing tasks on English as the only source corpus and on a wide range of target languages.

Copied to clipboard

Nam Nguyen, Thang Phan, Duc-Vu Nguyen, Kiet Nguyen

Improving Zero-Shot Cross-lingual Transfer Between Closely Related Languages by Injecting Character-Level Noise (2022.findings-acl)

Challenge:	English and Chinese have seen the strong development of transformer-based language models for natural language processing tasks.
Approach:	They present a monolingual pre-trained language model for Vietnamese social media texts . they explore emotion recognition, hate speech detection, sentiment analysis, spam reviews detection .
Outcome:	The proposed model outperforms the existing models on Vietnamese social media tasks with fewer parameters.

Copied to clipboard

Noëmi Aepli, Rico Sennrich

Design Challenges and Misconceptions in Neural Sequence Labeling (C18-1)

Challenge:	Existing approaches to improve cross-lingual transfer do not take surface similarity into account.
Approach:	They propose to augment source language training data with character-level noise to simulate spelling variations.
Outcome:	The proposed strategy shows consistent improvements over several languages and tasks.

Copied to clipboard

Jie Yang, Shuailong Liang, Yue Zhang

GLUECoS: An Evaluation Benchmark for Code-Switched NLP (2020.acl-main)

Challenge:	Existing neural sequence labeling models have been used for many tasks such as POS tagging, chunking and named entity recognition (NER).
Approach:	They propose to replicate twelve neural sequence labeling models and compare them to three benchmarks to find out which models are effective and which are inconsistent.
Outcome:	The proposed models are compared on NER, Chunking, and POS tagging benchmarks.

Copied to clipboard

Simran Khanuja, Sandipan Dandapat, Anirudh Srinivasan, Sunayana Sitaram, Monojit Choudhury

Multilinguality

Challenge:	Recent studies show multilingual contextual embedding models perform better on cross-lingual and multilingual tasks.
Approach:	They propose to evaluate multilingual contextual embedding models on multilingual data . they use language identification from text, POS tagging, Named Entity Recognition and Question Answering .
Outcome:	The proposed benchmark evaluates models on language identification from text, POS tagging, Named Entity Recognition, Question Answering and a new task for code-switching, Natural Language Inference.

Word Reordering for Zero-shot Cross-lingual Structured Prediction (2021.emnlp-main)

Copied to clipboard

Tao Ji, Yong Jiang, Tao Wang, Zhongqiang Huang, Fei Huang, Yuanbin Wu, Xiaoling Wang

Low-Resource NLP

Challenge:	Current sentence encoders are word order sensitive, resulting in poor performance . Adapting word order from one language to another is key in cross-lingual structured prediction.
Approach:	They propose a new module to organize words following the source language order . they build structured prediction models with bag-of-words inputs and introduce a module to do this .
Outcome:	The proposed model significantly improves target language performance for languages that are distant from the source language.

BKTreebank: Building a Vietnamese Dependency Treebank (L18-1)

Copied to clipboard

Kiem-Hieu Nguyen

Word Embeddings for Code-Mixed Language Processing (D18-1)

Challenge:	In this paper, we present the building of a dependency treebank for Vietnamese .
Approach:	They propose to build a Vietnamese dependency treebank using automatic taggers and automatic tagging.
Outcome:	The proposed treebank is a useful resource for Vietnamese language processing.

Copied to clipboard

Adithya Pratapa, Monojit Choudhury, Sunayana Sitaram

Representation Learning

Challenge:	Existing bilingual word embedding techniques are not ideal for code-mixed text processing and there is a need for learning multilingual word embeds from code-mixed texts.
Approach:	They propose to use bilingual word embedding techniques to train skip-grams on synthetic code-mixed text generated through linguistic models of code- mixing to perform two tasks.
Outcome:	The proposed embedding technique performs better on semantic and syntactic tasks than the existing embeddable techniques on sentiment analysis and POS tagging tasks.

Domain adaptation for part-of-speech tagging of noisy user-generated text (N19-1)

Copied to clipboard

Luisa März, Dietrich Trautmann, Benjamin Roth

Universal Dependencies for Amharic (L18-1)

Challenge:	Existing POS taggers for canonical German text achieve good results around 97% accuracy, but when applying these trained models to out-of-domain data the performance decreases drastically.
Approach:	They propose a neural network that trains an out-of-domain model on a large newswire corpus and transfers those weights by using them as a prior for a model trained on the target domain.
Outcome:	The proposed model achieves a tagging accuracy of slightly over 90%, improving on the previous state of the art for this task.

Copied to clipboard

Binyam Ephrem Seyoum, Yusuke Miyao, Baye Yimam Mekonnen

From Zero to Hero: On the Limitations of Zero-Shot Language Transfer with Multilingual Transformers (2020.emnlp-main)

Challenge:	Amharic is a morphologically rich language with a dependency relation between orthographic words and lexical categories.
Approach:	They propose to create an Amharic Dependency Treebank by POS tagging, morphological information and dependency relations.
Outcome:	The proposed treebanks are based on 1,096 sentences and are able to parse Amharic.

Copied to clipboard

Anne Lauscher, Vinit Ravishankar, Ivan Vulić, Goran Glavaš

Developing New Linguistic Resources and Tools for the Galician Language (L18-1)

Challenge:	Existing studies show that multilingual transformers are less effective in resource-lean scenarios and for distant languages.
Approach:	They propose to use massively multilingual transformers to pretrain languages . they show that MMTs are less effective in resource-lean scenarios and distant languages if they are pre-trained via language modeling .
Outcome:	The proposed model is less effective in resource-lean scenarios and for distant languages than cross-lingual word embeddings.

Copied to clipboard

Rodrigo Agerri, Xavier Gómez Guinovart, German Rigau, Miguel Anxo Solla Portela

Hierarchically-Refined Label Attention Network for Sequence Labeling (D19-1)

Challenge:	Existing resources and tools for the Galician language are lacking for other less-resourced languages, such as statistical tools for lemmatization and Named Entity Recognition.
Approach:	They propose to develop a manually revised corpus for POS tagging and lemmatization, and a new manually annotated corpus to train existing statistical tools for the Galician language.
Outcome:	The proposed resources include a new corpus for POS tagging and lemmatization, and a manually annotated corpus to handle Named Entity recognition.

Copied to clipboard

Leyang Cui, Yue Zhang

ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters (2023.emnlp-main)

Challenge:	Conditional random fields (CRF) is a powerful model for statistical sequence labeling, but it does not give much information gain over strong neural encoding.
Approach:	They propose a hierarchically-refined label attention network which captures potential long-term label dependency by giving each word incrementally refined label distributions with hierarchical attention.
Outcome:	The proposed model improves POS tagging accuracy and speeds up training and testing compared to the current model.

Copied to clipboard

Vipul Rathore, Rajdeep Dhingra, Parag Singla, null Mausam

What data should I include in my POS tagging training set? (2025.findings-emnlp)

Challenge:	Existing approaches to zero-shot cross-lingual transfer have focused on training with adapters of a single source and testing either with the target LA or LA of another related language.
Approach:	They propose to leverage LAs of multiple (linguistically or geographically related) source languages for more effective cross-lingual transfer instead of just one source LA . they extend their novel neural architecture, ZGUL, to settings where either (1) some unlabeled data or (2) few-shot training examples are available for the target language .
Outcome:	Extensive experimentation across four language groups, covering 15 unseen target languages, shows improvements of up to 3.2 average F1 points over baselines on POS tagging and NER tasks.

Copied to clipboard

Zoey Liu, Masoud Jasbi, Christan Grant, Kenji Sagae, Emily Prud’hommeaux

BERT Rediscovers the Classical NLP Pipeline (P19-1)

Challenge:	POS tagging is a crucial task for descriptive linguistics and language documentation . POS tags are not available in all languages, but are used for training sets for understudied languages .
Approach:	They compare POS tagging with in-context learning, active learning, and random sampling . they find that POS can deliver reasonable results for communities with limited resources .
Outcome:	The proposed training set for Indigenous and endangered languages performs better than random sampling.

Copied to clipboard

Ian Tenney, Dipanjan Das, Ellie Pavlick

Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter (2025.findings-acl)

Challenge:	Pre-trained text encoders have advanced the state of the art on many NLP tasks . Qualitative analysis reveals that the model can and often does adjust this pipeline dynamically .
Approach:	They aim to quantify where linguistic information is captured within a network model . they aim to use pre-trained text encoders to displace static word embeddings .
Outcome:	The proposed model can adjust the pipeline dynamically, revealing lower-level decisions on the basis of disambiguation from higher-level representations.

Copied to clipboard

Verena Blaschke, Masha Fedzechkina, Maartje Ter Hoeve

Cross-Lingual Transfer

Challenge:	Prior work on cross-lingual transfer often focuses on a small set of languages from a few language families and/or a single task.
Approach:	They analyze cross-lingual transfer for 263 languages from a wide variety of language families . they include three popular NLP tasks: POS tagging, dependency parsing, topic classification .
Outcome:	The proposed approach is based on linguistic similarity measures for 263 languages . the results show that the effect of linguistic similarities on transfer performance depends on a range of factors .

Language-Independent Approach for Morphological Disambiguation (2022.coling-1)

Copied to clipboard

Alymzhan Toleu, Gulmira Tolegen, Rustam Mussabayev

KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi (2020.coling-main)

Challenge:	Existing approaches for predicting complex morphological tags treat each analysis as a tag and apply sequence labeling models to perform tagging.
Approach:	They propose a language-independent approach which integrates all words, roots, POS and morpheme tags into vectors and computes the inner products between analyses and the contexts.
Outcome:	The proposed approach outperforms existing models on seven different languages while running about 6 and 33 times faster than MarMot and Seq2Seq, respectively.

Copied to clipboard

Rubungo Andre Niyongabo, Qu Hong, Julia Kreutzer, Li Huang

Information Extraction & Text Mining

Challenge:	low-resource African languages are traditionally left behind because of the lack of well-annotated data and effective preprocessing.
Approach:	They propose two news datasets for multi-class classification of news articles in two low-resource African languages.
Outcome:	The proposed datasets show that training embeddings on the higher-resourced Kinyarwanda yields successful cross-lingual transfer to Kirundi.

Empowering Low-Resource Regional Languages with Lexicons : A Comparative Study of NLP Tools for Morphosyntactic Analysis (2024.lrec-main)

Copied to clipboard

Cristina Garcia Holgado, Marianne Vergez-Couret

E:Calm Resource: a Resource for Studying Texts Produced by French Pupils and Students (2020.lrec-1)

Challenge:	a lack of human and financial resources makes integrating lexicon information to low-resource languages challenging.
Approach:	They propose to use a bilingual lexicon to integrate lexical information to low-resource language . they compare a lexiconal approach to a neural approach that uses a larger lexicone .
Outcome:	The proposed approach improves POS tagging while using different lexicon sizes.

Copied to clipboard

Lydia-Mai Ho-Dac, Serge Fleury, Claude Ponton

MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African languages (2023.acl-long)

Challenge:	É:CALM resource is constructed from handwritten texts produced in a variety of usual contexts of teaching.
Approach:	They describe the whole data processing established for digitizing and standardizing such manuscripts in order to provide an ecological resource for NLP, corpus linguistics and POS.
Outcome:	The E:CALM resource is constructed from hand-written texts produced in a variety of usual contexts of teaching.

Copied to clipboard

Cheikh M. Bamba Dione, David Ifeoluwa Adelani, Peter Nabende, Jesujoba Alabi, Thapelo Sindane, Happy Buzaaba, Shamsuddeen Hassan Muhammad, Chris Chinenye Emezue, Perez Ogayo, Anuoluwapo Aremu, Catherine Gitau, Derguene Mbaye, Jonathan Mukiibi, Blessing Sibanda, Bonaventure F. P. Dossou, Andiswa Bukula, Rooweither Mabuya, Allahsera Auguste Tapo, Edwin Munkoh-Buabeng, Victoire Memdjokam Koagne, Fatoumata Ouoba Kabore, Amelia Taylor, Godson Kalipe, Tebogo Macucwa, Vukosi Marivate, Tajuddeen Gwadabe, Mboning Tchiaze Elvis, Ikechukwu Onyenwe, Gratien Atindogbe, Tolulope Adelani, Idris Akinade, Olanrewaju Samuel, Marien Nahimana, Théogène Musabeyezu, Emile Niyomutabazi, Ester Chimhenga, Kudzai Gotosa, Patrick Mizha, Apelete Agbolo, Seydou Traore, Chinedu Uchechukwu, Aliyu Yusuf, Muhammad Abdullahi, Dietrich Klakow

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:	POS tagging is one of the fundamental steps for many natural language processing (NLP) applications.
Approach:	They present AfricaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages.
Outcome:	The proposed model improves POS tagging performance in unseen languages.

Copied to clipboard

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

Graph Based Semi-Supervised Learning Approach for Tamil POS tagging (L18-1)

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

Mokanarangan Thayaparan, Surangika Ranathunga, Uthayasanker Thayasivam

Information Retrieval

Challenge:	Parts of Speech (POS) tagging is challenging for low resourced languages such as Tamil . low resource Tamil does not have large POS annotated corpus to build good quality POS taggers using supervised machine learning techniques.
Approach:	They propose a graph-based semi-supervised learning approach to classify unlabelled data using a small POS labelled data set.
Outcome:	The proposed method achieves 0.8743 over 0.7333 produced by a CRF tagger for the same limited size corpus.

FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations (2021.emnlp-main)

Copied to clipboard

Lukas Lange, Heike Adel, Jannik Strötgen, Dietrich Klakow

Representation Learning

Challenge:	Recent work on word embeddings and pre-trained language models has shown the large impact of language representations on natural language processing (NLP) models across tasks and domains.
Approach:	They propose feature-based adversarial meta-embeddings with an attention function that is guided by word-specific properties, such as shape and frequency, to handle subword-based embeddings.
Outcome:	The proposed model improves performance in downstream tasks even with word embeddings from transformers.

From English to Code-Switching: Transfer Learning with Strong Morphological Clues (2020.acl-main)

Copied to clipboard

Gustavo Aguilar, Thamar Solorio

Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge (2020.acl-main)

Challenge:	Linguistic code-switching (CS) is an understudied area in natural language processing . lack of resources and annotated data makes it difficult to strive for progress in CS-related tasks.
Approach:	They propose a method to adapt monolingual models to code-switched text in various tasks . they transfer English knowledge from a pre-trained ELMo model to different code-paired languages .
Outcome:	The proposed method outperforms multilingual BERT and homologous CS-unaware models and provides state-of-the-art in CS tasks.

Copied to clipboard

Yuanhe Tian, Yan Song, Xiang Ao, Fei Xia, Xiaojun Quan, Tong Zhang, Yonggang Wang

Improving Chinese Named Entity Recognition with Multi-grained Words and Part-of-Speech Tags via Joint Modeling (2024.lrec-main)

Challenge:	Chinese word segmentation and part-of-speech tagging are important fundamental tasks in natural language processing.
Approach:	They propose a neural model for Chinese word segmentation and part-of-speech tagging . they incorporate context features and syntactic knowledge for each input character .
Outcome:	The proposed model can learn and benefit from existing tools, but its quality may be poor.

Copied to clipboard

Chenhui Dou, Chen Gong, Zhenghua Li, Zhefeng Wang, Baoxing Huai, Min Zhang

Diversifying language models for lesser-studied languages and language-usage contexts: A case of second language Korean (2023.findings-emnlp)

Challenge:	Named entity recognition (CNER) is a fundamental task in natural language processing (NLP).
Approach:	They propose a tree parsing approach for jointly modeling Chinese named entity recognition (CNER) with multi-grained word segmentation (MWS) and POS tagging tasks.
Outcome:	The proposed approach achieves better or comparable performance with current methods.

Copied to clipboard

Hakyung Sung, Gyu-Ho Shin

Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysis (2022.lrec-1)

Challenge:	Existing morpheme parsers/taggers do not work reliably and optimally for L2 data.
Approach:	They train a neural network model on varying L2 datasets and measure its morpheme parsing/POS tagging performance on L2 test sets.
Outcome:	The proposed model excels in domain-specific tokenization and POS tagging compared to the baseline model.

Copied to clipboard

Hang Jiang, Yining Hua, Doug Beeferman, Deb Roy

MaiBaam: A Multi-Dialectal Bavarian Universal Dependency Treebank (2024.lrec-main)

Challenge:	Social media data such as Twitter messages pose a particular challenge to NLP systems because of their short, noisy nature.
Approach:	They create a Twitter-based NER corpus and train Tweet NLP models on it . they annotate named entities in TB2 using Amazon Mechanical Turk .
Outcome:	The proposed model outperforms existing models on Twitter and other social media platforms.

Copied to clipboard

Verena Blaschke, Barbara Kovačić, Siyao Peng, Hinrich Schütze, Barbara Plank

ManNER & ManPOS: Pioneering NLP for Endangered Manchu Language (2024.lrec-main)

Challenge:	Despite the success of the Universal Dependencies (UD) project, there is still a lack of diversity within high-resource languages and their closely related non-standard languages and dialects.
Approach:	They propose to annotate Bavarian with part-of-speech and syntactic dependency information manually in UD and to highlight morphosyntactical differences between the closely related languages.
Outcome:	The proposed treebank covers multiple genres including wiki, fiction, grammar examples, social, non-fiction and Bavarian.

Copied to clipboard

Sangah Lee, Sungjoo Byun, Jean Seo, Minha Kang