@inproceedings{nguyen-etal-2020-bertweet,
title = "{BERT}weet: A pre-trained language model for {E}nglish Tweets",
author = "Nguyen, Dat Quoc and
Vu, Thanh and
Tuan Nguyen, Anh",
editor = "Liu, Qun and
Schlangen, David",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-demos.2/",
doi = "10.18653/v1/2020.emnlp-demos.2",
pages = "9--14",
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 \url{https://github.com/VinAIResearch/BERTweet}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2020-bertweet">
<titleInfo>
<title>BERTweet: A pre-trained language model for English Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dat</namePart>
<namePart type="given">Quoc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="family">Tuan Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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</abstract>
<identifier type="citekey">nguyen-etal-2020-bertweet</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-demos.2</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-demos.2/</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>9</start>
<end>14</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERTweet: A pre-trained language model for English Tweets
%A Nguyen, Dat Quoc
%A Vu, Thanh
%A Tuan Nguyen, Anh
%Y Liu, Qun
%Y Schlangen, David
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2020
%8 October
%I Association for Computational Linguistics
%C Online
%F nguyen-etal-2020-bertweet
%X 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
%R 10.18653/v1/2020.emnlp-demos.2
%U https://aclanthology.org/2020.emnlp-demos.2/
%U https://doi.org/10.18653/v1/2020.emnlp-demos.2
%P 9-14
Markdown (Informal)
[BERTweet: A pre-trained language model for English Tweets](https://aclanthology.org/2020.emnlp-demos.2/) (Nguyen et al., EMNLP 2020)
ACL
- Dat Quoc Nguyen, Thanh Vu, and Anh Tuan Nguyen. 2020. BERTweet: A pre-trained language model for English Tweets. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 9–14, Online. Association for Computational Linguistics.