{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bertweet-a-pre-trained-language-model-for","title":"BERTweet: A pre-trained language model for English Tweets","arxiv_id":"2005.10200","date":"2020-05-20","proceeding":"EMNLP 2020 11","authors":["Dat Quoc Nguyen","Thanh Vu","Anh Tuan Nguyen"],"abstract":"We present BERTweet, the first public large-scale pre-trained language model for English Tweets. Our BERTweet, having the same architecture as BERT-base (Devlin et al., 2019), is trained using the RoBERTa pre-training procedure (Liu et al., 2019). Experiments show that BERTweet outperforms strong baselines RoBERTa-base and XLM-R-base (Conneau et al., 2020), producing better performance results than the previous state-of-the-art models on three Tweet NLP tasks: Part-of-speech tagging, Named-entity recognition and text classification. We release BERTweet under the MIT License to facilitate future research and applications on Tweet data. Our BERTweet is available at https://github.com/VinAIResearch/BERTweet","url_abs":"https://arxiv.org/abs/2005.10200v2","url_pdf":"https://arxiv.org/pdf/2005.10200v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bertweet-a-pre-trained-language-model-for","repo_url":"https://github.com/VinAIResearch/BERTweet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"bertweet-a-pre-trained-language-model-for","repo_url":"https://github.com/cardiffnlp/tweeteval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"bertweet-a-pre-trained-language-model-for","repo_url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/bertweet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"part-of-speech-tagging","task_name":"Part-Of-Speech Tagging"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"xlm-r","task_name":"XLM-R"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/named-entity-recognition-on-wnut-2016","task":"Named Entity Recognition (NER)","dataset":"WNUT 2016","model":"BERTweet","rank_in_archive_order":7,"of":7,"metrics":{"F1":"52.1"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-wnut-2017","task":"Named Entity Recognition (NER)","dataset":"WNUT 2017","model":"BERTweet","rank_in_archive_order":9,"of":23,"metrics":{"F1":"56.5"},"uses_additional_data":false},{"leaderboard":"/sota/part-of-speech-tagging-on-ritter","task":"Part-Of-Speech Tagging","dataset":"Ritter","model":"BERTweet","rank_in_archive_order":4,"of":4,"metrics":{"Acc":"90.1"},"uses_additional_data":false},{"leaderboard":"/sota/part-of-speech-tagging-on-tweebank","task":"Part-Of-Speech Tagging","dataset":"Tweebank","model":"BERTweet","rank_in_archive_order":2,"of":3,"metrics":{"Acc":"95.2"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-tweeteval","task":"Sentiment Analysis","dataset":"TweetEval","model":"BERTweet","rank_in_archive_order":1,"of":7,"metrics":{"ALL":"67.9","Emoji":"33.4","Emotion":"79.3","Irony":"82.1","Offensive":"79.5","Sentiment":"73.4","Stance":"71.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.10200","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}