Multilingual Multiword Expression Identification Using Lateral Inhibition and Domain Adaptation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AAJAYHRXJ" target="_blank" >RIV/00216208:11320/23:AJAYHRXJ - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85161395398&doi=10.3390%2fmath11112548&partnerID=40&md5=d8d1ceb79982fced175e76b84cd85ef0" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85161395398&doi=10.3390%2fmath11112548&partnerID=40&md5=d8d1ceb79982fced175e76b84cd85ef0</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/math11112548" target="_blank" >10.3390/math11112548</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Multilingual Multiword Expression Identification Using Lateral Inhibition and Domain Adaptation

Popis výsledku v původním jazyce

"Correctly identifying multiword expressions (MWEs) is an important task for most natural language processing systems since their misidentification can result in ambiguity and misunderstanding of the underlying text. In this work, we evaluate the performance of the mBERT model for MWE identification in a multilingual context by training it on all 14 languages available in version 1.2 of the PARSEME corpus. We also incorporate lateral inhibition and language adversarial training into our methodology to create language-independent embeddings and improve its capabilities in identifying multiword expressions. The evaluation of our models shows that the approach employed in this work achieves better results compared to the best system of the PARSEME 1.2 competition, MTLB-STRUCT, on 11 out of 14 languages for global MWE identification and on 12 out of 14 languages for unseen MWE identification. Additionally, averaged across all languages, our best approach outperforms the MTLB-STRUCT system by 1.23% on global MWE identification and by 4.73% on unseen global MWE identification. © 2023 by the authors."

Název v anglickém jazyce

Multilingual Multiword Expression Identification Using Lateral Inhibition and Domain Adaptation

Popis výsledku anglicky

"Correctly identifying multiword expressions (MWEs) is an important task for most natural language processing systems since their misidentification can result in ambiguity and misunderstanding of the underlying text. In this work, we evaluate the performance of the mBERT model for MWE identification in a multilingual context by training it on all 14 languages available in version 1.2 of the PARSEME corpus. We also incorporate lateral inhibition and language adversarial training into our methodology to create language-independent embeddings and improve its capabilities in identifying multiword expressions. The evaluation of our models shows that the approach employed in this work achieves better results compared to the best system of the PARSEME 1.2 competition, MTLB-STRUCT, on 11 out of 14 languages for global MWE identification and on 12 out of 14 languages for unseen MWE identification. Additionally, averaged across all languages, our best approach outperforms the MTLB-STRUCT system by 1.23% on global MWE identification and by 4.73% on unseen global MWE identification. © 2023 by the authors."

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

"Mathematics"

ISSN

2227-7390

e-ISSN

—

Svazek periodika

11

Číslo periodika v rámci svazku

11

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

18

Strana od-do

1-18

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85161395398