@inproceedings{nath-etal-2022-generalized,
title = "A Generalized Method for Automated Multilingual Loanword Detection",
author = "Nath, Abhijnan and
Mahdipour Saravani, Sina and
Khebour, Ibrahim and
Mannan, Sheikh and
Li, Zihui and
Krishnaswamy, Nikhil",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.442/",
pages = "4996--5013",
abstract = "Loanwords are words incorporated from one language into another without translation. Suppose two words from distantly-related or unrelated languages sound similar and have a similar meaning. In that case, this is evidence of likely borrowing. This paper presents a method to automatically detect loanwords across various language pairs, accounting for differences in script, pronunciation and phonetic transformation by the borrowing language. We incorporate edit distance, semantic similarity measures, and phonetic alignment. We evaluate on 12 language pairs and achieve performance comparable to or exceeding state of the art methods on single-pair loanword detection tasks. We also demonstrate that multilingual models perform the same or often better than models trained on single language pairs and can potentially generalize to unseen language pairs with sufficient data, and that our method can exceed human performance on loanword detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nath-etal-2022-generalized">
<titleInfo>
<title>A Generalized Method for Automated Multilingual Loanword 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">Sina</namePart>
<namePart type="family">Mahdipour Saravani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Khebour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheikh</namePart>
<namePart type="family">Mannan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihui</namePart>
<namePart type="family">Li</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 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Loanwords are words incorporated from one language into another without translation. Suppose two words from distantly-related or unrelated languages sound similar and have a similar meaning. In that case, this is evidence of likely borrowing. This paper presents a method to automatically detect loanwords across various language pairs, accounting for differences in script, pronunciation and phonetic transformation by the borrowing language. We incorporate edit distance, semantic similarity measures, and phonetic alignment. We evaluate on 12 language pairs and achieve performance comparable to or exceeding state of the art methods on single-pair loanword detection tasks. We also demonstrate that multilingual models perform the same or often better than models trained on single language pairs and can potentially generalize to unseen language pairs with sufficient data, and that our method can exceed human performance on loanword detection.</abstract>
<identifier type="citekey">nath-etal-2022-generalized</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.442/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4996</start>
<end>5013</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Generalized Method for Automated Multilingual Loanword Detection
%A Nath, Abhijnan
%A Mahdipour Saravani, Sina
%A Khebour, Ibrahim
%A Mannan, Sheikh
%A Li, Zihui
%A Krishnaswamy, Nikhil
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F nath-etal-2022-generalized
%X Loanwords are words incorporated from one language into another without translation. Suppose two words from distantly-related or unrelated languages sound similar and have a similar meaning. In that case, this is evidence of likely borrowing. This paper presents a method to automatically detect loanwords across various language pairs, accounting for differences in script, pronunciation and phonetic transformation by the borrowing language. We incorporate edit distance, semantic similarity measures, and phonetic alignment. We evaluate on 12 language pairs and achieve performance comparable to or exceeding state of the art methods on single-pair loanword detection tasks. We also demonstrate that multilingual models perform the same or often better than models trained on single language pairs and can potentially generalize to unseen language pairs with sufficient data, and that our method can exceed human performance on loanword detection.
%U https://aclanthology.org/2022.coling-1.442/
%P 4996-5013
Markdown (Informal)
[A Generalized Method for Automated Multilingual Loanword Detection](https://aclanthology.org/2022.coling-1.442/) (Nath et al., COLING 2022)
ACL
- Abhijnan Nath, Sina Mahdipour Saravani, Ibrahim Khebour, Sheikh Mannan, Zihui Li, and Nikhil Krishnaswamy. 2022. A Generalized Method for Automated Multilingual Loanword Detection. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4996–5013, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.