@inproceedings{gautam-etal-2021-translate,
title = "Translate and Classify: Improving Sequence Level Classification for {E}nglish-{H}indi Code-Mixed Data",
author = "Gautam, Devansh and
Gupta, Kshitij and
Shrivastava, Manish",
editor = "Solorio, Thamar and
Chen, Shuguang and
Black, Alan W. and
Diab, Mona and
Sitaram, Sunayana and
Soto, Victor and
Yilmaz, Emre and
Srinivasan, Anirudh",
booktitle = "Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.calcs-1.3",
doi = "10.18653/v1/2021.calcs-1.3",
pages = "15--25",
abstract = "Code-mixing is a common phenomenon in multilingual societies around the world and is especially common in social media texts. Traditional NLP systems, usually trained on monolingual corpora, do not perform well on code-mixed texts. Training specialized models for code-switched texts is difficult due to the lack of large-scale datasets. Translating code-mixed data into standard languages like English could improve performance on various code-mixed tasks since we can use transfer learning from state-of-the-art English models for processing the translated data. This paper focuses on two sequence-level classification tasks for English-Hindi code mixed texts, which are part of the GLUECoS benchmark - Natural Language Inference and Sentiment Analysis. We propose using various pre-trained models that have been fine-tuned for similar English-only tasks and have shown state-of-the-art performance. We further fine-tune these models on the translated code-mixed datasets and achieve state-of-the-art performance in both tasks. To translate English-Hindi code-mixed data to English, we use mBART, a pre-trained multilingual sequence-to-sequence model that has shown competitive performance on various low-resource machine translation pairs and has also shown performance gains in languages that were not in its pre-training corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gautam-etal-2021-translate">
<titleInfo>
<title>Translate and Classify: Improving Sequence Level Classification for English-Hindi Code-Mixed Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Devansh</namePart>
<namePart type="family">Gautam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kshitij</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuguang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Black</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Soto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emre</namePart>
<namePart type="family">Yilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anirudh</namePart>
<namePart type="family">Srinivasan</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>Code-mixing is a common phenomenon in multilingual societies around the world and is especially common in social media texts. Traditional NLP systems, usually trained on monolingual corpora, do not perform well on code-mixed texts. Training specialized models for code-switched texts is difficult due to the lack of large-scale datasets. Translating code-mixed data into standard languages like English could improve performance on various code-mixed tasks since we can use transfer learning from state-of-the-art English models for processing the translated data. This paper focuses on two sequence-level classification tasks for English-Hindi code mixed texts, which are part of the GLUECoS benchmark - Natural Language Inference and Sentiment Analysis. We propose using various pre-trained models that have been fine-tuned for similar English-only tasks and have shown state-of-the-art performance. We further fine-tune these models on the translated code-mixed datasets and achieve state-of-the-art performance in both tasks. To translate English-Hindi code-mixed data to English, we use mBART, a pre-trained multilingual sequence-to-sequence model that has shown competitive performance on various low-resource machine translation pairs and has also shown performance gains in languages that were not in its pre-training corpus.</abstract>
<identifier type="citekey">gautam-etal-2021-translate</identifier>
<identifier type="doi">10.18653/v1/2021.calcs-1.3</identifier>
<location>
<url>https://aclanthology.org/2021.calcs-1.3</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>15</start>
<end>25</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translate and Classify: Improving Sequence Level Classification for English-Hindi Code-Mixed Data
%A Gautam, Devansh
%A Gupta, Kshitij
%A Shrivastava, Manish
%Y Solorio, Thamar
%Y Chen, Shuguang
%Y Black, Alan W.
%Y Diab, Mona
%Y Sitaram, Sunayana
%Y Soto, Victor
%Y Yilmaz, Emre
%Y Srinivasan, Anirudh
%S Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F gautam-etal-2021-translate
%X Code-mixing is a common phenomenon in multilingual societies around the world and is especially common in social media texts. Traditional NLP systems, usually trained on monolingual corpora, do not perform well on code-mixed texts. Training specialized models for code-switched texts is difficult due to the lack of large-scale datasets. Translating code-mixed data into standard languages like English could improve performance on various code-mixed tasks since we can use transfer learning from state-of-the-art English models for processing the translated data. This paper focuses on two sequence-level classification tasks for English-Hindi code mixed texts, which are part of the GLUECoS benchmark - Natural Language Inference and Sentiment Analysis. We propose using various pre-trained models that have been fine-tuned for similar English-only tasks and have shown state-of-the-art performance. We further fine-tune these models on the translated code-mixed datasets and achieve state-of-the-art performance in both tasks. To translate English-Hindi code-mixed data to English, we use mBART, a pre-trained multilingual sequence-to-sequence model that has shown competitive performance on various low-resource machine translation pairs and has also shown performance gains in languages that were not in its pre-training corpus.
%R 10.18653/v1/2021.calcs-1.3
%U https://aclanthology.org/2021.calcs-1.3
%U https://doi.org/10.18653/v1/2021.calcs-1.3
%P 15-25
Markdown (Informal)
[Translate and Classify: Improving Sequence Level Classification for English-Hindi Code-Mixed Data](https://aclanthology.org/2021.calcs-1.3) (Gautam et al., CALCS 2021)
ACL