@inproceedings{makhija-etal-2020-hinglishnorm,
title = "hinglish{N}orm - A Corpus of {H}indi-{E}nglish Code Mixed Sentences for Text Normalization",
author = "Makhija, Piyush and
Kumar, Ankit and
Gupta, Anuj",
editor = "Clifton, Ann and
Napoles, Courtney",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics: Industry Track",
month = dec,
year = "2020",
address = "Online",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-industry.13",
doi = "10.18653/v1/2020.coling-industry.13",
pages = "136--145",
abstract = "We present hinglishNorm - a human annotated corpus of Hindi-English code-mixed sentences for text normalization task. Each sentence in the corpus is aligned to its corresponding human annotated normalized form. To the best of our knowledge, there is no corpus of Hindi-English code-mixed sentences for text normalization task that is publicly available. Our work is the first attempt in this direction. The corpus contains 13494 segments annotated for text normalization. Further, we present baseline normalization results on this corpus. We obtain a Word Error Rate (WER) of 15.55, BiLingual Evaluation Understudy (BLEU) score of 71.2, and Metric for Evaluation of Translation with Explicit ORdering (METEOR) score of 0.50.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="makhija-etal-2020-hinglishnorm">
<titleInfo>
<title>hinglishNorm - A Corpus of Hindi-English Code Mixed Sentences for Text Normalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piyush</namePart>
<namePart type="family">Makhija</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankit</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Gupta</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 28th International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Clifton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Courtney</namePart>
<namePart type="family">Napoles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present hinglishNorm - a human annotated corpus of Hindi-English code-mixed sentences for text normalization task. Each sentence in the corpus is aligned to its corresponding human annotated normalized form. To the best of our knowledge, there is no corpus of Hindi-English code-mixed sentences for text normalization task that is publicly available. Our work is the first attempt in this direction. The corpus contains 13494 segments annotated for text normalization. Further, we present baseline normalization results on this corpus. We obtain a Word Error Rate (WER) of 15.55, BiLingual Evaluation Understudy (BLEU) score of 71.2, and Metric for Evaluation of Translation with Explicit ORdering (METEOR) score of 0.50.</abstract>
<identifier type="citekey">makhija-etal-2020-hinglishnorm</identifier>
<identifier type="doi">10.18653/v1/2020.coling-industry.13</identifier>
<location>
<url>https://aclanthology.org/2020.coling-industry.13</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>136</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T hinglishNorm - A Corpus of Hindi-English Code Mixed Sentences for Text Normalization
%A Makhija, Piyush
%A Kumar, Ankit
%A Gupta, Anuj
%Y Clifton, Ann
%Y Napoles, Courtney
%S Proceedings of the 28th International Conference on Computational Linguistics: Industry Track
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Online
%F makhija-etal-2020-hinglishnorm
%X We present hinglishNorm - a human annotated corpus of Hindi-English code-mixed sentences for text normalization task. Each sentence in the corpus is aligned to its corresponding human annotated normalized form. To the best of our knowledge, there is no corpus of Hindi-English code-mixed sentences for text normalization task that is publicly available. Our work is the first attempt in this direction. The corpus contains 13494 segments annotated for text normalization. Further, we present baseline normalization results on this corpus. We obtain a Word Error Rate (WER) of 15.55, BiLingual Evaluation Understudy (BLEU) score of 71.2, and Metric for Evaluation of Translation with Explicit ORdering (METEOR) score of 0.50.
%R 10.18653/v1/2020.coling-industry.13
%U https://aclanthology.org/2020.coling-industry.13
%U https://doi.org/10.18653/v1/2020.coling-industry.13
%P 136-145
Markdown (Informal)
[hinglishNorm - A Corpus of Hindi-English Code Mixed Sentences for Text Normalization](https://aclanthology.org/2020.coling-industry.13) (Makhija et al., COLING 2020)
ACL