@inproceedings{hadj-mohamed-etal-2024-lexicons,
title = "Lexicons Gain the Upper Hand in {A}rabic {MWE} Identification",
author = "Hadj Mohamed, Najet and
Savary, Agata and
Ben Khelil, Cherifa and
Antoine, Jean-Yves and
Keskes, Iskandar and
Hadrich-Belguith, Lamia",
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-1.13",
pages = "88--97",
abstract = "This paper highlights the importance of integrating MWE identification with the development of syntactic MWE lexicons. It suggests that lexicons with minimal morphosyntactic information can amplify current MWE-annotated datasets and refine identification strategies. To our knowledge, this work represents the first attempt to focus on both seen and unseen of VMWEs for Arabic. It also deals with the challenge of differentiating between literal and figurative interpretations of idiomatic expressions. The approach involves a dual-phase procedure: first projecting a VMWE lexicon onto a corpus to identify candidate occurrences, then disambiguating these occurrences to distinguish idiomatic from literal instances. Experiments outlined in the paper aim to assess the efficacy of this technique, utilizing a lexicon known as LEXAR and the {``}parseme-ar{''} corpus. The findings suggest that lexicon-driven strategies have the potential to refine MWE identification, particularly for unseen occurrences.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hadj-mohamed-etal-2024-lexicons">
<titleInfo>
<title>Lexicons Gain the Upper Hand in Arabic MWE Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Najet</namePart>
<namePart type="family">Hadj Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cherifa</namePart>
<namePart type="family">Ben Khelil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Yves</namePart>
<namePart type="family">Antoine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iskandar</namePart>
<namePart type="family">Keskes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="family">Hadrich-Belguith</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>This paper highlights the importance of integrating MWE identification with the development of syntactic MWE lexicons. It suggests that lexicons with minimal morphosyntactic information can amplify current MWE-annotated datasets and refine identification strategies. To our knowledge, this work represents the first attempt to focus on both seen and unseen of VMWEs for Arabic. It also deals with the challenge of differentiating between literal and figurative interpretations of idiomatic expressions. The approach involves a dual-phase procedure: first projecting a VMWE lexicon onto a corpus to identify candidate occurrences, then disambiguating these occurrences to distinguish idiomatic from literal instances. Experiments outlined in the paper aim to assess the efficacy of this technique, utilizing a lexicon known as LEXAR and the “parseme-ar” corpus. The findings suggest that lexicon-driven strategies have the potential to refine MWE identification, particularly for unseen occurrences.</abstract>
<identifier type="citekey">hadj-mohamed-etal-2024-lexicons</identifier>
<location>
<url>https://aclanthology.org/2024.mwe-1.13</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>88</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexicons Gain the Upper Hand in Arabic MWE Identification
%A Hadj Mohamed, Najet
%A Savary, Agata
%A Ben Khelil, Cherifa
%A Antoine, Jean-Yves
%A Keskes, Iskandar
%A Hadrich-Belguith, Lamia
%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 hadj-mohamed-etal-2024-lexicons
%X This paper highlights the importance of integrating MWE identification with the development of syntactic MWE lexicons. It suggests that lexicons with minimal morphosyntactic information can amplify current MWE-annotated datasets and refine identification strategies. To our knowledge, this work represents the first attempt to focus on both seen and unseen of VMWEs for Arabic. It also deals with the challenge of differentiating between literal and figurative interpretations of idiomatic expressions. The approach involves a dual-phase procedure: first projecting a VMWE lexicon onto a corpus to identify candidate occurrences, then disambiguating these occurrences to distinguish idiomatic from literal instances. Experiments outlined in the paper aim to assess the efficacy of this technique, utilizing a lexicon known as LEXAR and the “parseme-ar” corpus. The findings suggest that lexicon-driven strategies have the potential to refine MWE identification, particularly for unseen occurrences.
%U https://aclanthology.org/2024.mwe-1.13
%P 88-97
Markdown (Informal)
[Lexicons Gain the Upper Hand in Arabic MWE Identification](https://aclanthology.org/2024.mwe-1.13) (Hadj Mohamed et al., MWE-UDW-WS 2024)
ACL
- Najet Hadj Mohamed, Agata Savary, Cherifa Ben Khelil, Jean-Yves Antoine, Iskandar Keskes, and Lamia Hadrich-Belguith. 2024. Lexicons Gain the Upper Hand in Arabic MWE Identification. In Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024, pages 88–97, Torino, Italia. ELRA and ICCL.