Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3ANJN76SBY" target="_blank" >RIV/00216208:11320/23:NJN76SBY - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85161461930&partnerID=40&md5=e9d60a8caf5041520b5966a5dbebdf2c" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85161461930&partnerID=40&md5=e9d60a8caf5041520b5966a5dbebdf2c</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition

Popis výsledku v původním jazyce

"Multiword expressions are a key ingredient for developing large-scale and linguistically sound natural language processing technology. This paper describes our improvements in automatically identifying Romanian multiword expressions on the corpus released for the PARSEME v1.2 shared task. Our approach assumes a multilingual perspective based on the recently introduced lateral inhibition layer and adversarial training to boost the performance of the employed multilingual language models. With the help of these two methods, we improve the F1-score of XLM-RoBERTa by approximately 2.7% on unseen multiword expressions, the main task of the PARSEME 1.2 edition. In addition, our results can be considered SOTA performance, as they outperform the previous results on Romanian obtained by the participants in this competition. © 2023 Association for Computational Linguistics."

Název v anglickém jazyce

Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition

Popis výsledku anglicky

"Multiword expressions are a key ingredient for developing large-scale and linguistically sound natural language processing technology. This paper describes our improvements in automatically identifying Romanian multiword expressions on the corpus released for the PARSEME v1.2 shared task. Our approach assumes a multilingual perspective based on the recently introduced lateral inhibition layer and adversarial training to boost the performance of the employed multilingual language models. With the help of these two methods, we improve the F1-score of XLM-RoBERTa by approximately 2.7% on unseen multiword expressions, the main task of the PARSEME 1.2 edition. In addition, our results can be considered SOTA performance, as they outperform the previous results on Romanian obtained by the participants in this competition. © 2023 Association for Computational Linguistics."

Druh

D - Stať ve sborníku

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 statě ve sborníku

"Workshop Multiword Expressions, MWE - Proc."

ISBN

978-195942959-3

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

7-13

Název nakladatele

Association for Computational Linguistics

Místo vydání

—

Místo konání akce

Melaka, Malaysia

Datum konání akce

1. 1. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—