@inproceedings{srivastava-singh-2021-hinge,
title = "{H}in{GE}: A Dataset for Generation and Evaluation of Code-Mixed {H}inglish Text",
author = "Srivastava, Vivek and
Singh, Mayank",
editor = "Gao, Yang and
Eger, Steffen and
Zhao, Wei and
Lertvittayakumjorn, Piyawat and
Fomicheva, Marina",
booktitle = "Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eval4nlp-1.20",
doi = "10.18653/v1/2021.eval4nlp-1.20",
pages = "200--208",
abstract = "Text generation is a highly active area of research in the computational linguistic community. The evaluation of the generated text is a challenging task and multiple theories and metrics have been proposed over the years. Unfortunately, text generation and evaluation are relatively understudied due to the scarcity of high-quality resources in code-mixed languages where the words and phrases from multiple languages are mixed in a single utterance of text and speech. To address this challenge, we present a corpus (HinGE) for a widely popular code-mixed language Hinglish (code-mixing of Hindi and English languages). HinGE has Hinglish sentences generated by humans as well as two rule-based algorithms corresponding to the parallel Hindi-English sentences. In addition, we demonstrate the in- efficacy of widely-used evaluation metrics on the code-mixed data. The HinGE dataset will facilitate the progress of natural language generation research in code-mixed languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="srivastava-singh-2021-hinge">
<titleInfo>
<title>HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mayank</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Eger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyawat</namePart>
<namePart type="family">Lertvittayakumjorn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Fomicheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text generation is a highly active area of research in the computational linguistic community. The evaluation of the generated text is a challenging task and multiple theories and metrics have been proposed over the years. Unfortunately, text generation and evaluation are relatively understudied due to the scarcity of high-quality resources in code-mixed languages where the words and phrases from multiple languages are mixed in a single utterance of text and speech. To address this challenge, we present a corpus (HinGE) for a widely popular code-mixed language Hinglish (code-mixing of Hindi and English languages). HinGE has Hinglish sentences generated by humans as well as two rule-based algorithms corresponding to the parallel Hindi-English sentences. In addition, we demonstrate the in- efficacy of widely-used evaluation metrics on the code-mixed data. The HinGE dataset will facilitate the progress of natural language generation research in code-mixed languages.</abstract>
<identifier type="citekey">srivastava-singh-2021-hinge</identifier>
<identifier type="doi">10.18653/v1/2021.eval4nlp-1.20</identifier>
<location>
<url>https://aclanthology.org/2021.eval4nlp-1.20</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>200</start>
<end>208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Text
%A Srivastava, Vivek
%A Singh, Mayank
%Y Gao, Yang
%Y Eger, Steffen
%Y Zhao, Wei
%Y Lertvittayakumjorn, Piyawat
%Y Fomicheva, Marina
%S Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F srivastava-singh-2021-hinge
%X Text generation is a highly active area of research in the computational linguistic community. The evaluation of the generated text is a challenging task and multiple theories and metrics have been proposed over the years. Unfortunately, text generation and evaluation are relatively understudied due to the scarcity of high-quality resources in code-mixed languages where the words and phrases from multiple languages are mixed in a single utterance of text and speech. To address this challenge, we present a corpus (HinGE) for a widely popular code-mixed language Hinglish (code-mixing of Hindi and English languages). HinGE has Hinglish sentences generated by humans as well as two rule-based algorithms corresponding to the parallel Hindi-English sentences. In addition, we demonstrate the in- efficacy of widely-used evaluation metrics on the code-mixed data. The HinGE dataset will facilitate the progress of natural language generation research in code-mixed languages.
%R 10.18653/v1/2021.eval4nlp-1.20
%U https://aclanthology.org/2021.eval4nlp-1.20
%U https://doi.org/10.18653/v1/2021.eval4nlp-1.20
%P 200-208
Markdown (Informal)
[HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Text](https://aclanthology.org/2021.eval4nlp-1.20) (Srivastava & Singh, Eval4NLP 2021)
ACL