{"total":151,"rows":[{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560,"area":null},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492,"area":null},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168,"area":null},{"id":"2103.11811","title":"MasakhaNER: Named Entity Recognition for African Languages","created":"2021-03-22","cited_by_count":155,"area":null},{"id":"2204.06487","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","created":"2022-04-13","cited_by_count":149,"area":null},{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148,"area":null},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2205.02022","title":"A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation","created":"2022-05-04","cited_by_count":98,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2310.00907","title":"The Participatory Turn in AI Design: Theoretical Foundations and the Current State of Practice","created":"2023-10-02","cited_by_count":87,"area":null},{"id":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86,"area":null},{"id":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69,"area":null},{"id":"2205.15960","title":"NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages","created":"2022-05-31","cited_by_count":68,"area":null},{"id":"2201.08277","title":"NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis","created":"2022-01-20","cited_by_count":64,"area":null},{"id":"2402.01864","title":"(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice","created":"2024-02-02","cited_by_count":63,"area":null},{"id":"2209.12226","title":"Re-contextualizing Fairness in NLP: The Case of India","created":"2022-09-25","cited_by_count":55,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2212.10758","title":"ORCA: A Challenging Benchmark for Arabic Language Understanding","created":"2022-12-21","cited_by_count":47,"area":null},{"id":"2304.06845","title":"SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)","created":"2023-04-13","cited_by_count":41,"area":null},{"id":"2103.08647","title":"The Effect of Domain and Diacritics in Yor\\`ub\\'a-English Neural Machine Translation","created":"2021-03-15","cited_by_count":38,"area":null},{"id":"2210.12391","title":"MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition","created":"2022-10-22","cited_by_count":38,"area":null},{"id":"2306.07377","title":"Lost in Translation: Large Language Models in Non-English Content Analysis","created":"2023-06-12","cited_by_count":35,"area":null},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34,"area":null},{"id":"2405.19479","title":"Participation in the age of foundation models","created":"2024-05-29","cited_by_count":32,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2206.00437","title":"What a Creole Wants, What a Creole Needs","created":"2022-06-01","cited_by_count":27,"area":null},{"id":"2109.04715","title":"AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages","created":"2021-09-10","cited_by_count":24,"area":null},{"id":"2309.01859","title":"NLLB-CLIP -- train performant multilingual image retrieval model on a budget","created":"2023-09-04","cited_by_count":24,"area":null},{"id":"2305.06897","title":"AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languages","created":"2023-05-11","cited_by_count":23,"area":null},{"id":"2112.03497","title":"Dataset Geography: Mapping Language Data to Language Users","created":"2021-12-07","cited_by_count":22,"area":null},{"id":"2203.11764","title":"Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments","created":"2022-03-22","cited_by_count":22,"area":null},{"id":"2109.04593","title":"A Large-Scale Study of Machine Translation in the Turkic Languages","created":"2021-09-09","cited_by_count":21,"area":null},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2104.02516","title":"AI4D -- African Language Program","created":"2021-04-06","cited_by_count":18,"area":null},{"id":"2408.17024","title":"InkubaLM: A small language model for low-resource African languages","created":"2024-08-30","cited_by_count":18,"area":null},{"id":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15,"area":null},{"id":"2202.12288","title":"Toward More Meaningful Resources for Lower-resourced Languages","created":"2022-02-24","cited_by_count":14,"area":null},{"id":"2207.00688","title":"Building African Voices","created":"2022-07-01","cited_by_count":14,"area":null},{"id":"2103.07762","title":"OkwuGb\\'e: End-to-End Speech Recognition for Fon and Igbo","created":"2021-03-13","cited_by_count":13,"area":null},{"id":"2204.09391","title":"You Are What You Write: Preserving Privacy in the Era of Large Language Models","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2303.03750","title":"Preparing the Vuk'uzenzele and ZA-gov-multilingual South African multilingual corpora","created":"2023-03-07","cited_by_count":12,"area":null},{"id":"2410.20817","title":"The Zeno's Paradox of `Low-Resource' Languages","created":"2024-10-28","cited_by_count":12,"area":null},{"id":"2204.04306","title":"MMTAfrica: Multilingual Machine Translation for African Languages","created":"2022-04-08","cited_by_count":11,"area":null},{"id":"2406.19564","title":"Voices Unheard: NLP Resources and Models for Yor\\`ub\\'a Regional Dialects","created":"2024-06-27","cited_by_count":11,"area":null},{"id":"2210.15696","title":"COMET-QE and Active Learning for Low-Resource Machine Translation","created":"2022-10-27","cited_by_count":10,"area":null},{"id":"2211.00142","title":"TaTa: A Multilingual Table-to-Text Dataset for African Languages","created":"2022-10-31","cited_by_count":10,"area":null},{"id":"2208.12081","title":"Kencorpus: A Kenyan Language Corpus of Swahili, Dholuo and Luhya for Natural Language Processing Tasks","created":"2022-08-25","cited_by_count":9,"area":null},{"id":"2403.14791","title":"Particip-AI: A Democratic Surveying Framework for Anticipating Future AI Use Cases, Harms and Benefits","created":"2024-03-21","cited_by_count":9,"area":null},{"id":"2109.06262","title":"Evaluating Multiway Multilingual NMT in the Turkic Languages","created":"2021-09-13","cited_by_count":8,"area":null},{"id":"2203.12524","title":"Computational historical linguistics and language diversity in South Asia","created":"2022-03-23","cited_by_count":8,"area":null},{"id":"2305.06530","title":"How Good are Commercial Large Language Models on African Languages?","created":"2023-05-11","cited_by_count":8,"area":null},{"id":"2306.06804","title":"Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2505.20564","title":"The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2209.07611","title":"Corpus-Guided Contrast Sets for Morphosyntactic Feature Detection in Low-Resource English Varieties","created":"2022-09-15","cited_by_count":6,"area":null},{"id":"2210.10692","title":"Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages","created":"2022-10-19","cited_by_count":6,"area":null},{"id":"2310.03639","title":"Evaluating Self-Supervised Speech Representations for Indigenous American Languages","created":"2023-10-05","cited_by_count":6,"area":null},{"id":"2310.09141","title":"PuoBERTa: Training and evaluation of a curated language model for Setswana","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2503.12051","title":"TLUE: A Tibetan Language Understanding Evaluation Benchmark","created":"2025-03-15","cited_by_count":6,"area":null},{"id":"2103.10734","title":"Congolese Swahili Machine Translation for Humanitarian Response","created":"2021-03-19","cited_by_count":5,"area":null},{"id":"2103.15475","title":"NLP for Ghanaian Languages","created":"2021-03-29","cited_by_count":5,"area":null},{"id":"2104.05753","title":"Towards a parallel corpus of Portuguese and the Bantu language Emakhuwa of Mozambique","created":"2021-04-12","cited_by_count":5,"area":null},{"id":"2110.07444","title":"Designing Language Technologies for Social Good: The Road not Taken","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2111.06230","title":"Training Cross-Lingual embeddings for Setswana and Sepedi","created":"2021-11-11","cited_by_count":5,"area":null},{"id":"2112.11482","title":"English2Gbe: A multilingual machine translation model for {Fon/Ewe}Gbe","created":"2021-12-13","cited_by_count":5,"area":null},{"id":"2205.00965","title":"State-of-the-art in Open-domain Conversational AI: A Survey","created":"2022-05-02","cited_by_count":5,"area":null},{"id":"2305.00606","title":"Low-Resourced Machine Translation for Senegalese Wolof Language","created":"2023-05-01","cited_by_count":5,"area":null},{"id":"2405.16669","title":"Low-resourced Languages and Online Knowledge Repositories: A Need-Finding Study","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2406.08726","title":"Standard Language Ideology in AI-Generated Language","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2503.24102","title":"Is Small Language Model the Silver Bullet to Low-Resource Languages Machine Translation?","created":"2025-03-31","cited_by_count":5,"area":null},{"id":"2206.07861","title":"Text normalization for low-resource languages: the case of Ligurian","created":"2022-06-16","cited_by_count":4,"area":null},{"id":"2211.11206","title":"Cultural Re-contextualization of Fairness Research in Language Technologies in India","created":"2022-11-21","cited_by_count":4,"area":null},{"id":"2303.12582","title":"AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages","created":"2023-03-22","cited_by_count":4,"area":null},{"id":"2406.15358","title":"Introducing Syllable Tokenization for Low-resource Languages: A Case Study with Swahili","created":"2024-03-26","cited_by_count":4,"area":null},{"id":"2510.11557","title":"Invisible Languages of the LLM Universe","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2103.13272","title":"Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages","created":"2021-03-24","cited_by_count":3,"area":null},{"id":"2106.16055","title":"IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task","created":"2021-06-30","cited_by_count":3,"area":null},{"id":"2301.02773","title":"Building a Parallel Corpus and Training Translation Models Between Luganda and English","created":"2023-01-07","cited_by_count":3,"area":null},{"id":"2303.16985","title":"Adapting to the Low-Resource Double-Bind: Investigating Low-Compute Methods on Low-Resource African Languages","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2404.01009","title":"Constructing and Expanding Low-Resource and Underrepresented Parallel Datasets for Indonesian Local Languages","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2406.05888","title":"Feriji: A French-Zarma Parallel Corpus, Glossary & Translator","created":"2024-06-09","cited_by_count":3,"area":null},{"id":"2501.17899","title":"The Right to AI","created":"2025-01-29","cited_by_count":3,"area":null},{"id":"2503.03186","title":"Designing Speech Technologies for Australian Aboriginal English: Opportunities, Risks and Participation","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2603.13793","title":"GhanaNLP Parallel Corpora: Comprehensive Multilingual Resources for Low-Resource Ghanaian Languages","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2207.10524","title":"NusaCrowd: A Call for Open and Reproducible NLP Research in Indonesian Languages","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2310.15612","title":"Machine Translation for Nko: Tools, Corpora and Baseline Results","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2504.00289","title":"Do Chinese models speak Chinese languages?","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2510.25967","title":"Semantic Label Drift in Cross-Cultural Translation","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2511.10664","title":"Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkish","created":"2025-11-05","cited_by_count":2,"area":null},{"id":"2103.16190","title":"AfriKI: Machine-in-the-Loop Afrikaans Poetry Generation","created":"2021-03-30","cited_by_count":1,"area":null},{"id":"2204.02483","title":"Considerations for Multilingual Wikipedia Research","created":"2022-04-05","cited_by_count":1,"area":null},{"id":"2204.08083","title":"AfriWOZ: Corpus for Exploiting Cross-Lingual Transferability for Generation of Dialogues in Low-Resource, African Languages","created":"2022-04-17","cited_by_count":1,"area":null},{"id":"2205.15599","title":"Preparing an Endangered Language for the Digital Age: The Case of Judeo-Spanish","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2206.04039","title":"Resolving the Human Subjects Status of Machine Learning's Crowdworkers","created":"2022-06-08","cited_by_count":1,"area":null},{"id":"2308.14280","title":"FonMTL: Towards Multitask Learning for the Fon Language","created":"2023-08-28","cited_by_count":1,"area":null},{"id":"2409.01053","title":"A Perspective on Literary Metaphor in the Context of Generative AI","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2504.14105","title":"Amplify Initiative: Building A Localized Data Platform for Globalized AI","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2506.16782","title":"What Is the Point of Equality in Machine Learning Fairness? Beyond Equality of Opportunity","created":"2025-06-20","cited_by_count":1,"area":null}],"next_cursor":"100"}