@inproceedings{nath-etal-2022-phonetic,
title = "Phonetic, Semantic, and Articulatory Features in {A}ssamese-{B}engali Cognate Detection",
author = "Nath, Abhijnan and
Ghosh, Rahul and
Krishnaswamy, Nikhil",
editor = {Scherrer, Yves and
Jauhiainen, Tommi and
Ljube{\v{s}}i{\'c}, Nikola and
Nakov, Preslav and
Tiedemann, J{\"o}rg and
Zampieri, Marcos},
booktitle = "Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.vardial-1.5/",
pages = "41--53",
abstract = "In this paper, we propose a method to detect if words in two similar languages, Assamese and Bengali, are cognates. We mix phonetic, semantic, and articulatory features and use the cognate detection task to analyze the relative informational contribution of each type of feature to distinguish words in the two similar languages. In addition, since support for low-resourced languages like Assamese can be weak or nonexistent in some multilingual language models, we create a monolingual Assamese Transformer model and explore augmenting multilingual models with monolingual models using affine transformation techniques between vector spaces."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nath-etal-2022-phonetic">
<titleInfo>
<title>Phonetic, Semantic, and Articulatory Features in Assamese-Bengali Cognate Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhijnan</namePart>
<namePart type="family">Nath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">Krishnaswamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Jauhiainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose a method to detect if words in two similar languages, Assamese and Bengali, are cognates. We mix phonetic, semantic, and articulatory features and use the cognate detection task to analyze the relative informational contribution of each type of feature to distinguish words in the two similar languages. In addition, since support for low-resourced languages like Assamese can be weak or nonexistent in some multilingual language models, we create a monolingual Assamese Transformer model and explore augmenting multilingual models with monolingual models using affine transformation techniques between vector spaces.</abstract>
<identifier type="citekey">nath-etal-2022-phonetic</identifier>
<location>
<url>https://aclanthology.org/2022.vardial-1.5/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>41</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phonetic, Semantic, and Articulatory Features in Assamese-Bengali Cognate Detection
%A Nath, Abhijnan
%A Ghosh, Rahul
%A Krishnaswamy, Nikhil
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%Y Ljubešić, Nikola
%Y Nakov, Preslav
%Y Tiedemann, Jörg
%Y Zampieri, Marcos
%S Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F nath-etal-2022-phonetic
%X In this paper, we propose a method to detect if words in two similar languages, Assamese and Bengali, are cognates. We mix phonetic, semantic, and articulatory features and use the cognate detection task to analyze the relative informational contribution of each type of feature to distinguish words in the two similar languages. In addition, since support for low-resourced languages like Assamese can be weak or nonexistent in some multilingual language models, we create a monolingual Assamese Transformer model and explore augmenting multilingual models with monolingual models using affine transformation techniques between vector spaces.
%U https://aclanthology.org/2022.vardial-1.5/
%P 41-53
Markdown (Informal)
[Phonetic, Semantic, and Articulatory Features in Assamese-Bengali Cognate Detection](https://aclanthology.org/2022.vardial-1.5/) (Nath et al., VarDial 2022)
ACL