@inproceedings{sonawane-etal-2020-generating,
title = "Generating Inflectional Errors for Grammatical Error Correction in {H}indi",
author = "Sonawane, Ankur and
Vishwakarma, Sujeet Kumar and
Srivastava, Bhavana and
Kumar Singh, Anil",
editor = "Shmueli, Boaz and
Huang, Yin Jou",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-srw.24",
pages = "165--171",
abstract = "Automated grammatical error correction has been explored as an important research problem within NLP, with the majority of the work being done on English and similar resource-rich languages. Grammar correction using neural networks is a data-heavy task, with the recent state of the art models requiring datasets with millions of annotated sentences for proper training. It is difficult to find such resources for Indic languages due to their relative lack of digitized content and complex morphology, compared to English. We address this problem by generating a large corpus of artificial inflectional errors for training GEC models. Moreover, to evaluate the performance of models trained on this dataset, we create a corpus of real Hindi errors extracted from Wikipedia edits. Analyzing this dataset with a modified version of the ERRANT error annotation toolkit, we find that inflectional errors are very common in this language. Finally, we produce the initial baseline results using state of the art methods developed for English.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sonawane-etal-2020-generating">
<titleInfo>
<title>Generating Inflectional Errors for Grammatical Error Correction in Hindi</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankur</namePart>
<namePart type="family">Sonawane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujeet</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Vishwakarma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhavana</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anil</namePart>
<namePart type="family">Kumar Singh</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 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boaz</namePart>
<namePart type="family">Shmueli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yin</namePart>
<namePart type="given">Jou</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automated grammatical error correction has been explored as an important research problem within NLP, with the majority of the work being done on English and similar resource-rich languages. Grammar correction using neural networks is a data-heavy task, with the recent state of the art models requiring datasets with millions of annotated sentences for proper training. It is difficult to find such resources for Indic languages due to their relative lack of digitized content and complex morphology, compared to English. We address this problem by generating a large corpus of artificial inflectional errors for training GEC models. Moreover, to evaluate the performance of models trained on this dataset, we create a corpus of real Hindi errors extracted from Wikipedia edits. Analyzing this dataset with a modified version of the ERRANT error annotation toolkit, we find that inflectional errors are very common in this language. Finally, we produce the initial baseline results using state of the art methods developed for English.</abstract>
<identifier type="citekey">sonawane-etal-2020-generating</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-srw.24</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>165</start>
<end>171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Inflectional Errors for Grammatical Error Correction in Hindi
%A Sonawane, Ankur
%A Vishwakarma, Sujeet Kumar
%A Srivastava, Bhavana
%A Kumar Singh, Anil
%Y Shmueli, Boaz
%Y Huang, Yin Jou
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F sonawane-etal-2020-generating
%X Automated grammatical error correction has been explored as an important research problem within NLP, with the majority of the work being done on English and similar resource-rich languages. Grammar correction using neural networks is a data-heavy task, with the recent state of the art models requiring datasets with millions of annotated sentences for proper training. It is difficult to find such resources for Indic languages due to their relative lack of digitized content and complex morphology, compared to English. We address this problem by generating a large corpus of artificial inflectional errors for training GEC models. Moreover, to evaluate the performance of models trained on this dataset, we create a corpus of real Hindi errors extracted from Wikipedia edits. Analyzing this dataset with a modified version of the ERRANT error annotation toolkit, we find that inflectional errors are very common in this language. Finally, we produce the initial baseline results using state of the art methods developed for English.
%U https://aclanthology.org/2020.aacl-srw.24
%P 165-171
Markdown (Informal)
[Generating Inflectional Errors for Grammatical Error Correction in Hindi](https://aclanthology.org/2020.aacl-srw.24) (Sonawane et al., AACL 2020)
ACL
- Ankur Sonawane, Sujeet Kumar Vishwakarma, Bhavana Srivastava, and Anil Kumar Singh. 2020. Generating Inflectional Errors for Grammatical Error Correction in Hindi. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 165–171, Suzhou, China. Association for Computational Linguistics.