{"list":"other","total":61,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"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":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"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":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"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":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1611.01368","title":"Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies","created":"2016-11-04","cited_by_count":354},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"2004.13912","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","created":"2020-04-29","cited_by_count":319},{"id":"2012.15613","title":"How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models","created":"2020-12-31","cited_by_count":318},{"id":"2004.10643","title":"Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection","created":"2020-04-22","cited_by_count":271},{"id":"2002.05651","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","created":"2020-01-31","cited_by_count":249},{"id":"2004.03720","title":"Byte Pair Encoding is Suboptimal for Language Model Pretraining","created":"2020-04-07","cited_by_count":192},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172},{"id":"1905.12688","title":"Choosing Transfer Languages for Cross-Lingual Learning","created":"2019-05-29","cited_by_count":144},{"id":"2102.00894","title":"Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models","created":"2021-02-01","cited_by_count":132},{"id":"2012.15562","title":"UNKs Everywhere: Adapting Multilingual Language Models to New Scripts","created":"2020-12-31","cited_by_count":113},{"id":"1303.4402","title":"From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviews","created":"2013-03-18","cited_by_count":108},{"id":"2004.13640","title":"Extending Multilingual BERT to Low-Resource Languages","created":"2020-04-28","cited_by_count":88},{"id":"2102.00287","title":"Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation","created":"2021-01-30","cited_by_count":70},{"id":"1711.09576","title":"Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples","created":"2017-11-27","cited_by_count":66},{"id":"2011.01513","title":"CharBERT: Character-aware Pre-trained Language Model","created":"2020-11-03","cited_by_count":63},{"id":"2109.06860","title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","created":"2021-09-14","cited_by_count":59},{"id":"2012.15671","title":"Vocabulary Learning via Optimal Transport for Neural Machine Translation","created":"2020-12-31","cited_by_count":58},{"id":"1711.02013","title":"Neural Language Modeling by Jointly Learning Syntax and Lexicon","created":"2017-11-02","cited_by_count":57},{"id":"2005.00699","title":"Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer","created":"2020-05-02","cited_by_count":55},{"id":"1810.09648","title":"What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play","created":"2018-10-23","cited_by_count":53},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53},{"id":"2106.16171","title":"Revisiting the Primacy of English in Zero-shot Cross-lingual Transfer","created":"2021-06-30","cited_by_count":47},{"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":"2012.15682","title":"A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters","created":"2020-12-31","cited_by_count":45},{"id":"2006.06466","title":"How Interpretable and Trustworthy are GAMs?","created":"2020-06-11","cited_by_count":44},{"id":"2110.07038","title":"Towards Efficient NLP: A Standard Evaluation and A Strong Baseline","created":"2021-10-13","cited_by_count":44},{"id":"2002.10361","title":"Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition","created":"2020-02-24","cited_by_count":43},{"id":"2009.13888","title":"Utility is in the Eye of the User: A Critique of NLP Leaderboards","created":"2020-09-29","cited_by_count":28},{"id":"2106.00169","title":"Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation","created":"2021-06-01","cited_by_count":28},{"id":"2005.01330","title":"From SPMRL to NMRL: What Did We Learn (and Unlearn) in a Decade of Parsing Morphologically-Rich Languages (MRLs)?","created":"2020-05-04","cited_by_count":26},{"id":"1511.06052","title":"Overcoming Language Variation in Sentiment Analysis with Social Attention","created":"2015-11-19","cited_by_count":23},{"id":"2201.13405","title":"Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation","created":"2022-01-31","cited_by_count":23},{"id":"1809.04022","title":"Can LSTM Learn to Capture Agreement? The Case of Basque","created":"2018-09-11","cited_by_count":17},{"id":"2009.11982","title":"Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias","created":"2020-09-24","cited_by_count":15},{"id":"1704.08352","title":"From Characters to Words to in Between: Do We Capture Morphology?","created":"2017-04-26","cited_by_count":13},{"id":"2106.15355","title":"On the Interaction of Belief Bias and Explanations","created":"2021-06-29","cited_by_count":13},{"id":"1805.02214","title":"Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens","created":"2018-05-06","cited_by_count":12},{"id":"2109.10179","title":"How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings","created":"2021-09-21","cited_by_count":8},{"id":"1909.09428","title":"A Critical Analysis of Biased Parsers in Unsupervised Parsing","created":"2019-09-20","cited_by_count":7},{"id":"1704.01938","title":"The Interplay of Semantics and Morphology in Word Embeddings","created":"2017-04-06","cited_by_count":6},{"id":"2110.04384","title":"Evaluation of Summarization Systems across Gender, Age, and Race","created":"2021-10-08","cited_by_count":3}],"next_cursor":null}