{"list":"other","total":199,"rows":[{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2007.01852","title":"Language-agnostic BERT Sentence Embedding","created":"2020-07-03","cited_by_count":627},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601},{"id":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509},{"id":"2006.13979","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","created":"2020-06-24","cited_by_count":501},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"id":"1812.10464","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","created":"2018-12-26","cited_by_count":434},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243},{"id":"1907.05791","title":"WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia","created":"2019-07-10","cited_by_count":223},{"id":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192},{"id":"2309.04662","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","created":"2023-09-09","cited_by_count":181},{"id":"2309.09400","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","created":"2023-09-17","cited_by_count":174},{"id":"2406.09948","title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","created":"2024-06-14","cited_by_count":173},{"id":"2010.12309","title":"A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios","created":"2020-10-23","cited_by_count":171},{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152},{"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},{"id":"1905.12688","title":"Choosing Transfer Languages for Cross-Lingual Learning","created":"2019-05-29","cited_by_count":144},{"id":"2201.06642","title":"Towards a Cleaner Document-Oriented Multilingual Crawled Corpus","created":"2022-01-17","cited_by_count":143},{"id":"1911.06154","title":"CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs","created":"2019-11-10","cited_by_count":136},{"id":"2405.15032","title":"Aya 23: Open Weight Releases to Further Multilingual Progress","created":"2024-05-23","cited_by_count":123},{"id":"2011.12998","title":"VoxLingua107: a Dataset for Spoken Language Recognition","created":"2020-11-25","cited_by_count":122},{"id":"2406.05967","title":"CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark","created":"2024-06-10","cited_by_count":120},{"id":"2108.08787","title":"Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval","created":"2021-08-19","cited_by_count":119},{"id":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116},{"id":"2012.15562","title":"UNKs Everywhere: Adapting Multilingual Language Models to New Scripts","created":"2020-12-31","cited_by_count":113},{"id":"2010.12821","title":"Rethinking embedding coupling in pre-trained language models","created":"2020-10-24","cited_by_count":103},{"id":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101},{"id":"2407.10920","title":"Benchmarking Vision Language Models for Cultural Understanding","created":"2024-07-15","cited_by_count":101},{"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},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92},{"id":"2007.01788","title":"TICO-19: the Translation Initiative for Covid-19","created":"2020-07-03","cited_by_count":68},{"id":"2302.08956","title":"AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages","created":"2023-02-17","cited_by_count":68},{"id":"2305.14857","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","created":"2023-05-24","cited_by_count":68},{"id":"2406.06371","title":"mHuBERT-147: A Compact Multilingual HuBERT Model","created":"2024-06-10","cited_by_count":66},{"id":"2201.08277","title":"NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis","created":"2022-01-20","cited_by_count":64},{"id":"2406.00899","title":"YODAS: Youtube-Oriented Dataset for Audio and Speech","created":"2024-06-02","cited_by_count":60},{"id":"2108.03265","title":"Facebook AI WMT21 News Translation Task Submission","created":"2021-08-06","cited_by_count":57},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57},{"id":"2403.14009","title":"A New Massive Multilingual Dataset for High-Performance Language Technologies","created":"2024-03-20","cited_by_count":56},{"id":"2305.14328","title":"Benchmarking Machine Translation with Cultural Awareness","created":"2023-05-23","cited_by_count":53},{"id":"2010.03179","title":"Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages","created":"2020-10-07","cited_by_count":52},{"id":"2305.13820","title":"An Open Dataset and Model for Language Identification","created":"2023-05-23","cited_by_count":50},{"id":"2403.11009","title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages","created":"2024-03-16","cited_by_count":50},{"id":"2407.00837","title":"Towards Robust Speech Representation Learning for Thousands of Languages","created":"2024-06-30","cited_by_count":50},{"id":"2205.12654","title":"Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages","created":"2022-05-25","cited_by_count":48},{"id":"2407.05975","title":"LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages","created":"2024-07-08","cited_by_count":48},{"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},{"id":"2211.03263","title":"AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages","created":"2022-11-07","cited_by_count":46},{"id":"2404.18460","title":"Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in","created":"2024-04-29","cited_by_count":46},{"id":"2409.11404","title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","created":"2024-09-17","cited_by_count":46},{"id":"2203.09435","title":"Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation","created":"2022-03-17","cited_by_count":44},{"id":"2311.07978","title":"AfroBench: How Good are Large Language Models on African Languages?","created":"2023-11-14","cited_by_count":43},{"id":"2212.10785","title":"SERENGETI: Massively Multilingual Language Models for Africa","created":"2022-12-21","cited_by_count":40},{"id":"2112.08804","title":"CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs","created":"2021-12-16","cited_by_count":39},{"id":"2210.11744","title":"AfroLID: A Neural Language Identification Tool for African Languages","created":"2022-10-21","cited_by_count":39},{"id":"2410.12705","title":"WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines","created":"2024-10-16","cited_by_count":39},{"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},{"id":"2109.12072","title":"SD-QA: Spoken Dialectal Question Answering for the Real World","created":"2021-09-24","cited_by_count":38},{"id":"2311.08849","title":"OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining","created":"2023-11-15","cited_by_count":37},{"id":"2303.18110","title":"The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR","created":"2023-03-31","cited_by_count":36},{"id":"2310.00274","title":"AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR","created":"2023-09-30","cited_by_count":35},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34},{"id":"1912.02481","title":"Massive vs. Curated Word Embeddings for Low-Resourced Languages. The Case of Yor\\`ub\\'a and Twi","created":"2019-12-05","cited_by_count":33},{"id":"2207.03546","title":"BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus","created":"2022-07-07","cited_by_count":32},{"id":"2010.12174","title":"KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi","created":"2020-10-23","cited_by_count":31},{"id":"2210.14712","title":"Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks","created":"2022-10-26","cited_by_count":28},{"id":"2406.06196","title":"LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages","created":"2024-06-10","cited_by_count":28},{"id":"2209.02842","title":"ASR2K: Speech Recognition for Around 2000 Languages without Audio","created":"2022-09-06","cited_by_count":26},{"id":"2411.15640","title":"AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Dataset","created":"2024-11-23","cited_by_count":26},{"id":"2109.04715","title":"AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages","created":"2021-09-10","cited_by_count":24},{"id":"2305.14224","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","created":"2023-05-23","cited_by_count":24},{"id":"2311.09828","title":"AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages","created":"2023-11-16","cited_by_count":24},{"id":"2305.06897","title":"AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languages","created":"2023-05-11","cited_by_count":23},{"id":"2305.08487","title":"Taxi1500: A Multilingual Dataset for Text Classification in 1500 Languages","created":"2023-05-15","cited_by_count":23},{"id":"2305.13989","title":"MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages","created":"2023-05-23","cited_by_count":23},{"id":"2408.00397","title":"In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation","created":"2024-08-01","cited_by_count":22},{"id":"2406.12618","title":"From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP","created":"2024-06-18","cited_by_count":20},{"id":"2109.12346","title":"DziriBERT: a Pre-trained Language Model for the Algerian Dialect","created":"2021-09-25","cited_by_count":18},{"id":"2306.04428","title":"Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages","created":"2023-06-07","cited_by_count":18},{"id":"2311.10174","title":"JWSign: A Highly Multilingual Corpus of Bible Translations for more Diversity in Sign Language Processing","created":"2023-11-16","cited_by_count":18},{"id":"2402.18045","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","created":"2024-02-28","cited_by_count":18},{"id":"2408.17024","title":"InkubaLM: A small language model for low-resource African languages","created":"2024-08-30","cited_by_count":18},{"id":"2409.20201","title":"AfriHuBERT: A self-supervised speech representation model for African languages","created":"2024-09-30","cited_by_count":18}],"next_cursor":"100"}