Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition

Andrei Avram, Verginica Barbu Mititelu, Dumitru-Clementin Cercel


Abstract
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.
Anthology ID:
2023.mwe-1.4
Volume:
Proceedings of the 19th Workshop on Multiword Expressions (MWE 2023)
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Archna Bhatia, Kilian Evang, Marcos Garcia, Voula Giouli, Lifeng Han, Shiva Taslimipoor
Venue:
MWE
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
7–13
Language:
URL:
https://aclanthology.org/2023.mwe-1.4
DOI:
10.18653/v1/2023.mwe-1.4
Bibkey:
Cite (ACL):
Andrei Avram, Verginica Barbu Mititelu, and Dumitru-Clementin Cercel. 2023. Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition. In Proceedings of the 19th Workshop on Multiword Expressions (MWE 2023), pages 7–13, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition (Avram et al., MWE 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.mwe-1.4.pdf
Video:
 https://aclanthology.org/2023.mwe-1.4.mp4