@inproceedings{yayavaram-etal-2024-bert,
title = "{BERT}-based Idiom Identification using Language Translation and Word Cohesion",
author = "Yayavaram, Arnav and
Yayavaram, Siddharth and
Upadhyay, Prajna Devi and
Das, Apurba",
editor = {Bhatia, Archna and
Bouma, Gosse and
Do{\u{g}}ru{\"o}z, A. Seza and
Evang, Kilian and
Garcia, Marcos and
Giouli, Voula and
Han, Lifeng and
Nivre, Joakim and
Rademaker, Alexandre},
booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.mwe-1.26",
pages = "220--230",
abstract = "An idiom refers to a special type of multi-word expression whose meaning is figurative and cannot be deduced from the literal interpretation of its components. Idioms are prevalent in almost all languages and text genres, necessitating explicit handling by comprehensive NLP systems. Such phrases are referred to as Potentially Idiomatic Expressions (PIEs) and automatically identifying them in text is a challenging task. In this paper, we propose using a BERT-based model fine-tuned with custom objectives, to improve the accuracy of detecting PIEs in text. Our custom loss functions capture two important properties (word cohesion and language translation) to distinguish PIEs from non-PIEs. We conducted several experiments on 7 datasets and showed that incorporating custom objectives while training the model leads to substantial gains. Our models trained using this approach also have better sequence accuracy over DISC, a state-of-the-art PIE detection technique, along with good transfer capabilities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yayavaram-etal-2024-bert">
<titleInfo>
<title>BERT-based Idiom Identification using Language Translation and Word Cohesion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arnav</namePart>
<namePart type="family">Yayavaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Yayavaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prajna</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Upadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apurba</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Archna</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gosse</namePart>
<namePart type="family">Bouma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilian</namePart>
<namePart type="family">Evang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Voula</namePart>
<namePart type="family">Giouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>An idiom refers to a special type of multi-word expression whose meaning is figurative and cannot be deduced from the literal interpretation of its components. Idioms are prevalent in almost all languages and text genres, necessitating explicit handling by comprehensive NLP systems. Such phrases are referred to as Potentially Idiomatic Expressions (PIEs) and automatically identifying them in text is a challenging task. In this paper, we propose using a BERT-based model fine-tuned with custom objectives, to improve the accuracy of detecting PIEs in text. Our custom loss functions capture two important properties (word cohesion and language translation) to distinguish PIEs from non-PIEs. We conducted several experiments on 7 datasets and showed that incorporating custom objectives while training the model leads to substantial gains. Our models trained using this approach also have better sequence accuracy over DISC, a state-of-the-art PIE detection technique, along with good transfer capabilities.</abstract>
<identifier type="citekey">yayavaram-etal-2024-bert</identifier>
<location>
<url>https://aclanthology.org/2024.mwe-1.26</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>220</start>
<end>230</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERT-based Idiom Identification using Language Translation and Word Cohesion
%A Yayavaram, Arnav
%A Yayavaram, Siddharth
%A Upadhyay, Prajna Devi
%A Das, Apurba
%Y Bhatia, Archna
%Y Bouma, Gosse
%Y Doğruöz, A. Seza
%Y Evang, Kilian
%Y Garcia, Marcos
%Y Giouli, Voula
%Y Han, Lifeng
%Y Nivre, Joakim
%Y Rademaker, Alexandre
%S Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F yayavaram-etal-2024-bert
%X An idiom refers to a special type of multi-word expression whose meaning is figurative and cannot be deduced from the literal interpretation of its components. Idioms are prevalent in almost all languages and text genres, necessitating explicit handling by comprehensive NLP systems. Such phrases are referred to as Potentially Idiomatic Expressions (PIEs) and automatically identifying them in text is a challenging task. In this paper, we propose using a BERT-based model fine-tuned with custom objectives, to improve the accuracy of detecting PIEs in text. Our custom loss functions capture two important properties (word cohesion and language translation) to distinguish PIEs from non-PIEs. We conducted several experiments on 7 datasets and showed that incorporating custom objectives while training the model leads to substantial gains. Our models trained using this approach also have better sequence accuracy over DISC, a state-of-the-art PIE detection technique, along with good transfer capabilities.
%U https://aclanthology.org/2024.mwe-1.26
%P 220-230
Markdown (Informal)
[BERT-based Idiom Identification using Language Translation and Word Cohesion](https://aclanthology.org/2024.mwe-1.26) (Yayavaram et al., MWE-UDW-WS 2024)
ACL