@inproceedings{yadav-etal-2022-normalization,
title = "Normalization of Spelling Variations in Code-Mixed Data",
author = "Yadav, Krishna and
Akhtar, Md and
Chakraborty, Tanmoy",
editor = "Akhtar, Md. Shad and
Chakraborty, Tanmoy",
booktitle = "Proceedings of the 19th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2022",
address = "New Delhi, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.icon-main.33",
pages = "269--279",
abstract = "Code-mixed text infused with low resource language has always been a challenge for natural language understanding models. A significant problem while understanding such texts is the correlation between the syntactic and semantic arrangement of words. The phonemes of each character in a word dictates the spelling representation of a term in low resource language. However, there is no universal protocol or alphabet mapping for code-mixing. In this paper, we highlight the impact of spelling variations in code-mixed data for training natural language understanding models. We emphasize the impact of using phonetics to neutralize this variation in spelling across different usage of a word with the same semantics. The proposed approach is a computationally inexpensive technique and improves the performances of state-of-the-art models for three dialog system tasks \textit{viz.} intent classification, slot-filling, and response generation. We propose a data pipeline for normalizing spelling variations irrespective of language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadav-etal-2022-normalization">
<titleInfo>
<title>Normalization of Spelling Variations in Code-Mixed Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Krishna</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Shad</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Delhi, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-mixed text infused with low resource language has always been a challenge for natural language understanding models. A significant problem while understanding such texts is the correlation between the syntactic and semantic arrangement of words. The phonemes of each character in a word dictates the spelling representation of a term in low resource language. However, there is no universal protocol or alphabet mapping for code-mixing. In this paper, we highlight the impact of spelling variations in code-mixed data for training natural language understanding models. We emphasize the impact of using phonetics to neutralize this variation in spelling across different usage of a word with the same semantics. The proposed approach is a computationally inexpensive technique and improves the performances of state-of-the-art models for three dialog system tasks viz. intent classification, slot-filling, and response generation. We propose a data pipeline for normalizing spelling variations irrespective of language.</abstract>
<identifier type="citekey">yadav-etal-2022-normalization</identifier>
<location>
<url>https://aclanthology.org/2022.icon-main.33</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>269</start>
<end>279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Normalization of Spelling Variations in Code-Mixed Data
%A Yadav, Krishna
%A Akhtar, Md
%A Chakraborty, Tanmoy
%Y Akhtar, Md. Shad
%Y Chakraborty, Tanmoy
%S Proceedings of the 19th International Conference on Natural Language Processing (ICON)
%D 2022
%8 December
%I Association for Computational Linguistics
%C New Delhi, India
%F yadav-etal-2022-normalization
%X Code-mixed text infused with low resource language has always been a challenge for natural language understanding models. A significant problem while understanding such texts is the correlation between the syntactic and semantic arrangement of words. The phonemes of each character in a word dictates the spelling representation of a term in low resource language. However, there is no universal protocol or alphabet mapping for code-mixing. In this paper, we highlight the impact of spelling variations in code-mixed data for training natural language understanding models. We emphasize the impact of using phonetics to neutralize this variation in spelling across different usage of a word with the same semantics. The proposed approach is a computationally inexpensive technique and improves the performances of state-of-the-art models for three dialog system tasks viz. intent classification, slot-filling, and response generation. We propose a data pipeline for normalizing spelling variations irrespective of language.
%U https://aclanthology.org/2022.icon-main.33
%P 269-279
Markdown (Informal)
[Normalization of Spelling Variations in Code-Mixed Data](https://aclanthology.org/2022.icon-main.33) (Yadav et al., ICON 2022)
ACL
- Krishna Yadav, Md Akhtar, and Tanmoy Chakraborty. 2022. Normalization of Spelling Variations in Code-Mixed Data. In Proceedings of the 19th International Conference on Natural Language Processing (ICON), pages 269–279, New Delhi, India. Association for Computational Linguistics.