{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"2005.04790","title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","created":"2020-05-10","cited_by_count":490},{"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":"2005.00547","title":"GoEmotions: A Dataset of Fine-Grained Emotions","created":"2020-05-01","cited_by_count":486},{"id":"2302.09210","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","created":"2023-02-18","cited_by_count":348},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"1910.07475","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","created":"2019-10-16","cited_by_count":340},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293},{"id":"2202.01279","title":"PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts","created":"2022-02-02","cited_by_count":289},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231},{"id":"2004.01401","title":"XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation","created":"2020-04-03","cited_by_count":222},{"id":"1912.00741","title":"SemEval-2017 Task 4: Sentiment Analysis in Twitter","created":"2019-12-02","cited_by_count":210},{"id":"2304.05613","title":"ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning","created":"2023-04-12","cited_by_count":206},{"id":"2101.01785","title":"ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic","created":"2020-12-27","cited_by_count":166},{"id":"2103.07769","title":"Automated Fact-Checking for Assisting Human Fact-Checkers","created":"2021-03-13","cited_by_count":144},{"id":"1801.07883","title":"Deep Learning for Sentiment Analysis : A Survey","created":"2018-01-24","cited_by_count":139},{"id":"2006.07235","title":"SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)","created":"2020-06-12","cited_by_count":138},{"id":"1910.03814","title":"Exploring Hate Speech Detection in Multimodal Publications","created":"2019-10-09","cited_by_count":103},{"id":"2006.03644","title":"Stance Detection on Social Media: State of the Art and Trends","created":"2020-06-05","cited_by_count":95},{"id":"2005.00033","title":"Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society","created":"2020-04-30","cited_by_count":72},{"id":"1810.01765","title":"Predicting Factuality of Reporting and Bias of News Media Sources","created":"2018-10-02","cited_by_count":71},{"id":"2211.13892","title":"Complementary Explanations for Effective In-Context Learning","created":"2022-11-25","cited_by_count":71},{"id":"1709.07276","title":"Speech Recognition Challenge in the Wild: Arabic MGB-3","created":"2017-09-21","cited_by_count":60},{"id":"2205.04274","title":"Detecting and Understanding Harmful Memes: A Survey","created":"2022-05-09","cited_by_count":58},{"id":"1809.08193","title":"Towards Automated Factchecking: Developing an Annotation Schema and Benchmark for Consistent Automated Claim Detection","created":"2018-09-21","cited_by_count":55},{"id":"1906.05394","title":"Neural Arabic Question Answering","created":"2019-06-12","cited_by_count":48},{"id":"2212.10758","title":"ORCA: A Challenging Benchmark for Arabic Language Understanding","created":"2022-12-21","cited_by_count":47},{"id":"2005.06557","title":"Arabic Dialect Identification in the Wild","created":"2020-05-13","cited_by_count":45},{"id":"2109.08013","title":"Detecting Propaganda Techniques in Memes","created":"2021-08-07","cited_by_count":44},{"id":"1804.08012","title":"Integrating Stance Detection and Fact Checking in a Unified Corpus","created":"2018-04-21","cited_by_count":41},{"id":"2007.07996","title":"Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Arms","created":"2020-07-15","cited_by_count":41},{"id":"2105.14779","title":"Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR","created":"2021-05-31","cited_by_count":41},{"id":"2106.13000","title":"QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpus","created":"2021-06-24","cited_by_count":38},{"id":"2005.10410","title":"Stance Prediction and Claim Verification: An Arabic Perspective","created":"2020-05-21","cited_by_count":25},{"id":"1808.07674","title":"Arap-Tweet: A Large Multi-Dialect Twitter Corpus for Gender, Age and Language Variety Identification","created":"2018-08-23","cited_by_count":23},{"id":"2112.08544","title":"NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge","created":"2021-12-16","cited_by_count":20},{"id":"2107.01573","title":"Arabic Code-Switching Speech Recognition using Monolingual Data","created":"2021-07-04","cited_by_count":17},{"id":"1909.09691","title":"NSURL-2019 Shared Task 8: Semantic Question Similarity in Arabic","created":"2019-09-12","cited_by_count":7},{"id":"2206.07373","title":"NatiQ: An End-to-end Text-to-Speech System for Arabic","created":"2022-06-15","cited_by_count":7},{"id":"1707.07276","title":"Seminar Users in the Arabic Twitter Sphere","created":"2017-07-23","cited_by_count":5},{"id":"1709.00616","title":"Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging","created":"2017-09-02","cited_by_count":5},{"id":"1710.06700","title":"Build Fast and Accurate Lemmatization for Arabic","created":"2017-10-18","cited_by_count":3},{"id":"1810.06619","title":"Diacritization of Maghrebi Arabic Sub-Dialects","created":"2018-10-15","cited_by_count":2},{"id":"2203.00271","title":"ArabGend: Gender Analysis and Inference on Arabic Twitter","created":"2022-03-01","cited_by_count":2}],"next_cursor":null}