{"list":"other","total":60,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"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":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"1904.05342","title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","created":"2019-04-10","cited_by_count":493},{"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":"1908.10063","title":"FinBERT: Financial Sentiment Analysis with Pre-trained Language Models","created":"2019-08-27","cited_by_count":385},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"2005.10200","title":"BERTweet: A pre-trained language model for English Tweets","created":"2020-05-20","cited_by_count":346},{"id":"1904.09077","title":"Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT","created":"2019-04-19","cited_by_count":301},{"id":"1605.09096","title":"Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change","created":"2016-05-30","cited_by_count":221},{"id":"2005.09093","title":"Are All Languages Created Equal in Multilingual BERT?","created":"2020-05-18","cited_by_count":207},{"id":"1912.07840","title":"Cross-Lingual Ability of Multilingual BERT: An Empirical Study","created":"2019-12-17","cited_by_count":182},{"id":"1911.01464","title":"Emerging Cross-lingual Structure in Pretrained Language Models","created":"2019-11-04","cited_by_count":181},{"id":"1903.05987","title":"To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks","created":"2019-03-14","cited_by_count":167},{"id":"2004.02105","title":"Unsupervised Domain Clusters in Pretrained Language Models","created":"2020-04-05","cited_by_count":160},{"id":"2005.00770","title":"Exploring and Predicting Transferability across NLP Tasks","created":"2020-05-02","cited_by_count":128},{"id":"2007.11464","title":"SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection","created":"2020-07-22","cited_by_count":108},{"id":"2004.12376","title":"GLUECoS : An Evaluation Benchmark for Code-Switched NLP","created":"2020-04-26","cited_by_count":102},{"id":"2004.14118","title":"Analysing Lexical Semantic Change with Contextualised Word Representations","created":"2020-04-29","cited_by_count":92},{"id":"2004.13640","title":"Extending Multilingual BERT to Low-Resource Languages","created":"2020-04-28","cited_by_count":88},{"id":"2005.04364","title":"It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations","created":"2020-05-09","cited_by_count":64},{"id":"1906.00742","title":"Gender-preserving Debiasing for Pre-trained Word Embeddings","created":"2019-06-03","cited_by_count":61},{"id":"1405.3515","title":"Temporal Analysis of Language through Neural Language Models","created":"2014-05-14","cited_by_count":54},{"id":"1702.08359","title":"Dynamic Word Embeddings","created":"2017-02-27","cited_by_count":51},{"id":"1908.09324","title":"Multilingual Neural Machine Translation with Language Clustering","created":"2019-08-25","cited_by_count":47},{"id":"2009.05021","title":"Investigating Gender Bias in BERT","created":"2020-09-10","cited_by_count":40},{"id":"2002.07306","title":"From English To Foreign Languages: Transferring Pre-trained Language Models","created":"2020-02-18","cited_by_count":37},{"id":"1508.07544","title":"Computational Sociolinguistics: A Survey","created":"2015-08-30","cited_by_count":35},{"id":"2006.09075","title":"PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Models","created":"2020-06-16","cited_by_count":33},{"id":"1906.02979","title":"A Wind of Change: Detecting and Evaluating Lexical Semantic Change across Times and Domains","created":"2019-06-07","cited_by_count":31},{"id":"2010.12707","title":"Learning to Recognize Dialect Features","created":"2020-10-23","cited_by_count":29},{"id":"1909.00437","title":"Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation","created":"2019-09-01","cited_by_count":27},{"id":"1911.00202","title":"Forget Me Not: Reducing Catastrophic Forgetting for Domain Adaptation in Reading Comprehension","created":"2019-11-01","cited_by_count":27},{"id":"2004.03354","title":"Inexpensive Domain Adaptation of Pretrained Language Models: Case Studies on Biomedical NER and Covid-19 QA","created":"2020-04-07","cited_by_count":23},{"id":"1612.07486","title":"Continuous multilinguality with language vectors","created":"2016-12-22","cited_by_count":20},{"id":"2010.01150","title":"Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media","created":"2020-10-02","cited_by_count":16},{"id":"2010.01739","title":"Effective Unsupervised Domain Adaptation with Adversarially Trained Language Models","created":"2020-10-05","cited_by_count":12},{"id":"2010.11091","title":"TweetBERT: A Pretrained Language Representation Model for Twitter Text Analysis","created":"2020-10-17","cited_by_count":12},{"id":"1405.4392","title":"That's sick dude!: Automatic identification of word sense change across different timescales","created":"2014-05-17","cited_by_count":11},{"id":"1708.04358","title":"Continuous Representation of Location for Geolocation and Lexical Dialectology using Mixture Density Networks","created":"2017-08-14","cited_by_count":8},{"id":"2006.07698","title":"Transferring Monolingual Model to Low-Resource Language: The Case of Tigrinya","created":"2020-06-13","cited_by_count":8},{"id":"2010.03481","title":"ELMo and BERT in semantic change detection for Russian","created":"2020-10-07","cited_by_count":8},{"id":"1911.02655","title":"Towards Domain Adaptation from Limited Data for Question Answering Using Deep Neural Networks","created":"2019-11-06","cited_by_count":7},{"id":"1510.06786","title":"Freshman or Fresher? Quantifying the Geographic Variation of Internet Language","created":"2015-10-22","cited_by_count":6},{"id":"1703.08052","title":"Dynamic Bernoulli Embeddings for Language Evolution","created":"2017-03-23","cited_by_count":6},{"id":"1911.03913","title":"Can Monolingual Pretrained Models Help Cross-Lingual Classification?","created":"2019-11-10","cited_by_count":6},{"id":"2011.03258","title":"OP-IMS @ DIACR-Ita: Back to the Roots: SGNS+OP+CD still rocks Semantic Change Detection","created":"2020-11-06","cited_by_count":5},{"id":"2004.02288","title":"Continual Domain-Tuning for Pretrained Language Models","created":"2020-04-05","cited_by_count":4}],"next_cursor":null}