@inproceedings{gautam-2022-leveraging,
title = "Leveraging Sub Label Dependencies in Code Mixed {I}ndian Languages for Part-Of-Speech Tagging using Conditional Random Fields.",
author = "Gautam, Akash Kumar",
editor = "Jha, Girish Nath and
L., Sobha and
Bali, Kalika and
Ojha, Atul Kr.",
booktitle = "Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.wildre-1.3",
pages = "13--17",
abstract = "Code-mixed text sequences often lead to challenges in the task of correct identification of Part-Of-Speech tags. However, lexical dependencies created while alternating between multiple languages can be leveraged to improve the performance of such tasks. Indian languages with rich morphological structure and highly inflected nature provide such an opportunity. In this work, we exploit these sub-label dependencies using conditional random fields (CRFs) by defining feature extraction functions on three distinct language pairs (Hindi-English, Bengali-English, and Telugu-English). Our results demonstrate a significant increase in the tagging performance if the feature extraction functions employ the rich inner structure of such languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gautam-2022-leveraging">
<titleInfo>
<title>Leveraging Sub Label Dependencies in Code Mixed Indian Languages for Part-Of-Speech Tagging using Conditional Random Fields.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akash</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Gautam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Girish</namePart>
<namePart type="given">Nath</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">L.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-mixed text sequences often lead to challenges in the task of correct identification of Part-Of-Speech tags. However, lexical dependencies created while alternating between multiple languages can be leveraged to improve the performance of such tasks. Indian languages with rich morphological structure and highly inflected nature provide such an opportunity. In this work, we exploit these sub-label dependencies using conditional random fields (CRFs) by defining feature extraction functions on three distinct language pairs (Hindi-English, Bengali-English, and Telugu-English). Our results demonstrate a significant increase in the tagging performance if the feature extraction functions employ the rich inner structure of such languages.</abstract>
<identifier type="citekey">gautam-2022-leveraging</identifier>
<location>
<url>https://aclanthology.org/2022.wildre-1.3</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>13</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Sub Label Dependencies in Code Mixed Indian Languages for Part-Of-Speech Tagging using Conditional Random Fields.
%A Gautam, Akash Kumar
%Y Jha, Girish Nath
%Y L., Sobha
%Y Bali, Kalika
%Y Ojha, Atul Kr.
%S Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F gautam-2022-leveraging
%X Code-mixed text sequences often lead to challenges in the task of correct identification of Part-Of-Speech tags. However, lexical dependencies created while alternating between multiple languages can be leveraged to improve the performance of such tasks. Indian languages with rich morphological structure and highly inflected nature provide such an opportunity. In this work, we exploit these sub-label dependencies using conditional random fields (CRFs) by defining feature extraction functions on three distinct language pairs (Hindi-English, Bengali-English, and Telugu-English). Our results demonstrate a significant increase in the tagging performance if the feature extraction functions employ the rich inner structure of such languages.
%U https://aclanthology.org/2022.wildre-1.3
%P 13-17
Markdown (Informal)
[Leveraging Sub Label Dependencies in Code Mixed Indian Languages for Part-Of-Speech Tagging using Conditional Random Fields.](https://aclanthology.org/2022.wildre-1.3) (Gautam, WILDRE 2022)
ACL