@inproceedings{agarwal-etal-2022-bilingual,
title = "Bilingual Tabular Inference: A Case Study on {I}ndic Languages",
author = "Agarwal, Chaitanya and
Gupta, Vivek and
Kunchukuttan, Anoop and
Shrivastava, Manish",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.295/",
doi = "10.18653/v1/2022.naacl-main.295",
pages = "4018--4037",
abstract = "Existing research on Tabular Natural Language Inference (TNLI) exclusively examines the task in a monolingual setting where the tabular premise and hypothesis are in the same language. However, due to the uneven distribution of text resources on the web across languages, it is common to have the tabular premise in a high resource language and the hypothesis in a low resource language. As a result, we present the challenging task of bilingual Tabular Natural Language Inference (bTNLI), in which the tabular premise and a hypothesis over it are in two separate languages. We construct EI-InfoTabS: an English-Indic bTNLI dataset by translating the textual hypotheses of the English TNLI dataset InfoTabS into eleven major Indian languages. We thoroughly investigate how pre-trained multilingual models learn and perform on EI-InfoTabS. Our study shows that the performance on bTNLI can be close to its monolingual counterpart, with translate-train, translate-test and unified-train being strongly competitive baselines."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agarwal-etal-2022-bilingual">
<titleInfo>
<title>Bilingual Tabular Inference: A Case Study on Indic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaitanya</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kunchukuttan</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>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing research on Tabular Natural Language Inference (TNLI) exclusively examines the task in a monolingual setting where the tabular premise and hypothesis are in the same language. However, due to the uneven distribution of text resources on the web across languages, it is common to have the tabular premise in a high resource language and the hypothesis in a low resource language. As a result, we present the challenging task of bilingual Tabular Natural Language Inference (bTNLI), in which the tabular premise and a hypothesis over it are in two separate languages. We construct EI-InfoTabS: an English-Indic bTNLI dataset by translating the textual hypotheses of the English TNLI dataset InfoTabS into eleven major Indian languages. We thoroughly investigate how pre-trained multilingual models learn and perform on EI-InfoTabS. Our study shows that the performance on bTNLI can be close to its monolingual counterpart, with translate-train, translate-test and unified-train being strongly competitive baselines.</abstract>
<identifier type="citekey">agarwal-etal-2022-bilingual</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.295</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.295/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>4018</start>
<end>4037</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Tabular Inference: A Case Study on Indic Languages
%A Agarwal, Chaitanya
%A Gupta, Vivek
%A Kunchukuttan, Anoop
%A Shrivastava, Manish
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F agarwal-etal-2022-bilingual
%X Existing research on Tabular Natural Language Inference (TNLI) exclusively examines the task in a monolingual setting where the tabular premise and hypothesis are in the same language. However, due to the uneven distribution of text resources on the web across languages, it is common to have the tabular premise in a high resource language and the hypothesis in a low resource language. As a result, we present the challenging task of bilingual Tabular Natural Language Inference (bTNLI), in which the tabular premise and a hypothesis over it are in two separate languages. We construct EI-InfoTabS: an English-Indic bTNLI dataset by translating the textual hypotheses of the English TNLI dataset InfoTabS into eleven major Indian languages. We thoroughly investigate how pre-trained multilingual models learn and perform on EI-InfoTabS. Our study shows that the performance on bTNLI can be close to its monolingual counterpart, with translate-train, translate-test and unified-train being strongly competitive baselines.
%R 10.18653/v1/2022.naacl-main.295
%U https://aclanthology.org/2022.naacl-main.295/
%U https://doi.org/10.18653/v1/2022.naacl-main.295
%P 4018-4037
Markdown (Informal)
[Bilingual Tabular Inference: A Case Study on Indic Languages](https://aclanthology.org/2022.naacl-main.295/) (Agarwal et al., NAACL 2022)
ACL
- Chaitanya Agarwal, Vivek Gupta, Anoop Kunchukuttan, and Manish Shrivastava. 2022. Bilingual Tabular Inference: A Case Study on Indic Languages. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4018–4037, Seattle, United States. Association for Computational Linguistics.