Latest

• DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages
• A Case Study on Filtering for End-to-End Speech Translation
• Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing
• Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization
• A Morphologically-Aware Dictionary-based Data Augmentation Technique for Machine Translation of Under-Represented Languages
• Clinical Risk Prediction Using Language Models: Benefits And Considerations
• An Efficient Approach for Studying Cross-Lingual Transfer in Multilingual Language Models
• Are Large Language Models Geospatially Knowledgeable?
• Global Voices, Local Biases: Socio-Cultural Prejudices across Languages
• GlobalBench: A Benchmark for Global Progress in Natural Language Processing
• LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages
• Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning
• To token or not to token: A Comparative Study of Text Representations for Cross-Lingual Transfer
• CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation
• Towards a Universal Python: Translating the Natural Modality of Python into Other Human Languages
• Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages
• Script Normalization for Unconventional Writing of Under-Resourced Languages in Bilingual Communities
• BIG-C: a Multimodal Multi-Purpose Dataset for Bemba
• Approaches to Corpus Creation for Low-Resource Language Technology: the Case of Southern Kurdish and Laki
• PALI: A Language Identification Benchmark for Perso-Arabic Scripts
• GMNLP at SemEval-2023 Tasks 12: Sentiment Analysis with Phylogeny-Based Adapters
• Noisy Parallel Data Alignment
• Geographic and Geopolitical Biases of Language Models
• Findings of the WMT’22 Shared Task on Large-Scale Machine Translation Evaluation for African Languages
• Language Adapters for Large-Scale MT: The GMU System for the WMT 2022 Large-Scale Machine Translation Evaluation for African Languages Shared Task
• Phylogeny-Inspired Adaptation of Multilingual Models to New Languages
• The GMU System Submission for the SUMEval 2022 Shared Task
• Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey
• Educational Tools for Mapuzugun
• Dataset Geography: Mapping Language Data to Language Users
• Revisiting the Effects of Leakage on Dependency Parsing
• AUTOLEX: An Automatic Framework for Linguistic Exploration
• Lexically-Aware Semi-Supervised Learning for OCR Post-Correction
• Systematic Inequalities in Language Technology Performance across the World’s Languages
• When is Wall a Pared and when a Muro?: Extracting Rules Governing Lexical Selection
• Evaluating the Morphosyntactic Well-formedness of Generated Texts
• Findings of the WMT Shared Task on Machine Translation Using Terminologies
• Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering
• SD-QA: Spoken Dialectal Question Answering for the Real World
• Cross-Lingual Text Classification of Transliterated Hindi and Malayalam
• Dataset Maps - MasakhaNER (all)
• Dataset Maps - MLQA (English)
• Dataset Maps - Natural Questions (English)
• Dataset Maps - SQuAD (English)
• Dataset Maps - TyDi-QA (all)
• Dataset Maps - WikiANN (all)
• Dataset Maps - X-FACTR (12 languages)
• Information Intelligence
• Language and Code
• Language Models
• OCR
• Machine Translation into Low-resource Language Varieties
• Towards more equitable question answering systems: How much more data do you need?
• Code to Comment Translation: A Comparative Study on Model Effectiveness & Errors
• Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
• BembaSpeech: A Speech Recognition Corpus for the Bemba Language
• When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual LMs
• Reducing Confusion in Active Learning for Part-Of-Speech Tagging
• Automatic Interlinear Glossing for Under-Resourced Languages Leveraging Translations
• Automatic Extraction of Rules Governing Morphological Agreement
• Fine-Tuning MT systems for Robustness to Second-Language Speaker Variations
• It's not a Non-Issue: Negation as a Source of Error in Machine Translation
• OCR Post-Correction for Endangered Language Texts
• TICO-19: the Translation Initiative for COvid-19
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages
• Fairness
• Speech
• Morphology
• Robustness
• Language Documentation
• Machine Translation
• It′s Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information
• Optimizing Data Usage via Differentiable Rewards
• Predicting Performance for Natural Language Processing Tasks
• Proceedings of the The Fourth Widening Natural Language Processing Workshop
• Should All Cross-Lingual Embeddings Speak English?
• SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection
• The CMU-LTI submission to the SIGMORPHON 2020 Shared Task 0: Language-Specific Cross-Lingual Transfer
• Transliteration for Cross-Lingual Morphological Inflection
• Predicting Performance for Natural Language Processing Tasks
• Should All Cross-Lingual Embeddings Speak English?
• A note on evaluating multilingual benchmarks
• A Resource for Computational Experiments on Mapudungun
• A Resource for Studying Chatino Verbal Morphology
• A Summary of the First Workshop on Language Technology for Language Documentation and Revitalization
• AlloVera: A Multilingual Allophone Database
• Universal Phone Recognition with a Multilingual Allophone System
• Neural language modeling with visual features
• Practical Comparable Data Collection for Low-Resource Languages via Images
• Towards Robust Toxic Content Classification
• Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Tasks
• Pushing the Limits of Low-Resource Morphological Inflection
• Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings
• An Analysis of Source-Side Grammatical Errors in NMT
• Findings of the First Shared Task on Machine Translation Robustness
• Improving Robustness of Neural Machine Translation with Multi-task Learning
• Choosing Transfer Languages for Cross-Lingual Learning
• Generalized Data Augmentation for Low-Resource Translation
• Neural Machine Translation of Text from Non-Native Speakers
• Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource
• Tied Multitask Learning for Neural Speech Translation
• An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages
• An Attentional Model for Speech Translation Without Transcription