@inproceedings{kanojia-etal-2019-utilizing,
title = "Utilizing Wordnets for Cognate Detection among {I}ndian Languages",
author = "Kanojia, Diptesh and
Patel, Kevin and
Kulkarni, Malhar and
Bhattacharyya, Pushpak and
Haffari, Gholemreza",
editor = "Vossen, Piek and
Fellbaum, Christiane",
booktitle = "Proceedings of the 10th Global Wordnet Conference",
month = jul,
year = "2019",
address = "Wroclaw, Poland",
publisher = "Global Wordnet Association",
url = "https://aclanthology.org/2019.gwc-1.51",
pages = "404--412",
abstract = "Automatic Cognate Detection (ACD) is a challenging task which has been utilized to help NLP applications like Machine Translation, Information Retrieval and Computational Phylogenetics. Unidentified cognate pairs can pose a challenge to these applications and result in a degradation of performance. In this paper, we detect cognate word pairs among ten Indian languages with Hindi and use deep learning methodologies to predict whether a word pair is cognate or not. We identify IndoWordnet as a potential resource to detect cognate word pairs based on orthographic similarity-based methods and train neural network models using the data obtained from it. We identify parallel corpora as another potential resource and perform the same experiments for them. We also validate the contribution of Wordnets through further experimentation and report improved performance of up to 26{\%}. We discuss the nuances of cognate detection among closely related Indian languages and release the lists of detected cognates as a dataset. We also observe the behaviour of, to an extent, unrelated Indian language pairs and release the lists of detected cognates among them as well.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kanojia-etal-2019-utilizing">
<titleInfo>
<title>Utilizing Wordnets for Cognate Detection among Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diptesh</namePart>
<namePart type="family">Kanojia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Patel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malhar</namePart>
<namePart type="family">Kulkarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholemreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Global Wordnet Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christiane</namePart>
<namePart type="family">Fellbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Global Wordnet Association</publisher>
<place>
<placeTerm type="text">Wroclaw, Poland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic Cognate Detection (ACD) is a challenging task which has been utilized to help NLP applications like Machine Translation, Information Retrieval and Computational Phylogenetics. Unidentified cognate pairs can pose a challenge to these applications and result in a degradation of performance. In this paper, we detect cognate word pairs among ten Indian languages with Hindi and use deep learning methodologies to predict whether a word pair is cognate or not. We identify IndoWordnet as a potential resource to detect cognate word pairs based on orthographic similarity-based methods and train neural network models using the data obtained from it. We identify parallel corpora as another potential resource and perform the same experiments for them. We also validate the contribution of Wordnets through further experimentation and report improved performance of up to 26%. We discuss the nuances of cognate detection among closely related Indian languages and release the lists of detected cognates as a dataset. We also observe the behaviour of, to an extent, unrelated Indian language pairs and release the lists of detected cognates among them as well.</abstract>
<identifier type="citekey">kanojia-etal-2019-utilizing</identifier>
<location>
<url>https://aclanthology.org/2019.gwc-1.51</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>404</start>
<end>412</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Utilizing Wordnets for Cognate Detection among Indian Languages
%A Kanojia, Diptesh
%A Patel, Kevin
%A Kulkarni, Malhar
%A Bhattacharyya, Pushpak
%A Haffari, Gholemreza
%Y Vossen, Piek
%Y Fellbaum, Christiane
%S Proceedings of the 10th Global Wordnet Conference
%D 2019
%8 July
%I Global Wordnet Association
%C Wroclaw, Poland
%F kanojia-etal-2019-utilizing
%X Automatic Cognate Detection (ACD) is a challenging task which has been utilized to help NLP applications like Machine Translation, Information Retrieval and Computational Phylogenetics. Unidentified cognate pairs can pose a challenge to these applications and result in a degradation of performance. In this paper, we detect cognate word pairs among ten Indian languages with Hindi and use deep learning methodologies to predict whether a word pair is cognate or not. We identify IndoWordnet as a potential resource to detect cognate word pairs based on orthographic similarity-based methods and train neural network models using the data obtained from it. We identify parallel corpora as another potential resource and perform the same experiments for them. We also validate the contribution of Wordnets through further experimentation and report improved performance of up to 26%. We discuss the nuances of cognate detection among closely related Indian languages and release the lists of detected cognates as a dataset. We also observe the behaviour of, to an extent, unrelated Indian language pairs and release the lists of detected cognates among them as well.
%U https://aclanthology.org/2019.gwc-1.51
%P 404-412
Markdown (Informal)
[Utilizing Wordnets for Cognate Detection among Indian Languages](https://aclanthology.org/2019.gwc-1.51) (Kanojia et al., GWC 2019)
ACL