@inproceedings{bao-etal-2020-will-go,
title = "Will{\_}go at {S}em{E}val-2020 Task 9: An Accurate Approach for Sentiment Analysis on {H}indi-{E}nglish Tweets Based on Bert and Pesudo Label Strategy",
author = "Bao, Wei and
Chen, Weilong and
Bai, Wei and
Zhuang, Yan and
Cheng, Mingyuan and
Ma, Xiangyu",
editor = "Herbelot, Aurelie and
Zhu, Xiaodan and
Palmer, Alexis and
Schneider, Nathan and
May, Jonathan and
Shutova, Ekaterina",
booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
month = dec,
year = "2020",
address = "Barcelona (online)",
publisher = "International Committee for Computational Linguistics",
url = "https://aclanthology.org/2020.semeval-1.182",
doi = "10.18653/v1/2020.semeval-1.182",
pages = "1348--1353",
abstract = "Mixing languages are widely used in social media, especially in multilingual societies like India. Detecting the emotions contained in these languages, which is of great significance to the development of society and political trends. In this paper, we propose an ensemble of pesudo-label based Bert model and TFIDF based SGDClassifier model to identify the sentiments of Hindi-English (Hi-En) code-mixed data. The ensemble model combines the strengths of rich semantic information from the Bert model and word frequency information from the probabilistic ngram model to predict the sentiment of a given code-mixed tweet. Finally our team got an average F1 score of 0.731 on the final leaderboard,and our codalab username is will{\_}go.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-etal-2020-will-go">
<titleInfo>
<title>Will_go at SemEval-2020 Task 9: An Accurate Approach for Sentiment Analysis on Hindi-English Tweets Based on Bert and Pesudo Label Strategy</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weilong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyuan</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyu</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Semantic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Mixing languages are widely used in social media, especially in multilingual societies like India. Detecting the emotions contained in these languages, which is of great significance to the development of society and political trends. In this paper, we propose an ensemble of pesudo-label based Bert model and TFIDF based SGDClassifier model to identify the sentiments of Hindi-English (Hi-En) code-mixed data. The ensemble model combines the strengths of rich semantic information from the Bert model and word frequency information from the probabilistic ngram model to predict the sentiment of a given code-mixed tweet. Finally our team got an average F1 score of 0.731 on the final leaderboard,and our codalab username is will_go.</abstract>
<identifier type="citekey">bao-etal-2020-will-go</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.182</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.182</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1348</start>
<end>1353</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Will_go at SemEval-2020 Task 9: An Accurate Approach for Sentiment Analysis on Hindi-English Tweets Based on Bert and Pesudo Label Strategy
%A Bao, Wei
%A Chen, Weilong
%A Bai, Wei
%A Zhuang, Yan
%A Cheng, Mingyuan
%A Ma, Xiangyu
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y May, Jonathan
%Y Shutova, Ekaterina
%S Proceedings of the Fourteenth Workshop on Semantic Evaluation
%D 2020
%8 December
%I International Committee for Computational Linguistics
%C Barcelona (online)
%F bao-etal-2020-will-go
%X Mixing languages are widely used in social media, especially in multilingual societies like India. Detecting the emotions contained in these languages, which is of great significance to the development of society and political trends. In this paper, we propose an ensemble of pesudo-label based Bert model and TFIDF based SGDClassifier model to identify the sentiments of Hindi-English (Hi-En) code-mixed data. The ensemble model combines the strengths of rich semantic information from the Bert model and word frequency information from the probabilistic ngram model to predict the sentiment of a given code-mixed tweet. Finally our team got an average F1 score of 0.731 on the final leaderboard,and our codalab username is will_go.
%R 10.18653/v1/2020.semeval-1.182
%U https://aclanthology.org/2020.semeval-1.182
%U https://doi.org/10.18653/v1/2020.semeval-1.182
%P 1348-1353
Markdown (Informal)
[Will_go at SemEval-2020 Task 9: An Accurate Approach for Sentiment Analysis on Hindi-English Tweets Based on Bert and Pesudo Label Strategy](https://aclanthology.org/2020.semeval-1.182) (Bao et al., SemEval 2020)
ACL