Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition

2023/04/22 by Andrei-Marius Avram, Avram, Andrei-Marius, Verginica Barbu Mititelu +3 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2304.11350

openalex publication_date 2023/04/22 · openalex created_date 2023/04/27 · openalex updated_date 2026/07/28

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.

Cited by

• It's Not a Walk in the Park! Challenges of Idiom Translation in Speech-to-text Systems

Related

• Multilingual Multiword Expression Identification Using Lateral Inhibition and Domain Adaptation
• FuLG: 150B Romanian Corpus for Language Model Pretraining
• "Vorbeşti Româneşte?" A Recipe to Train Powerful Romanian LLMs with English Instructions
• Investigating the Impact of Semi-Supervised Methods with Data Augmentation on Offensive Language Detection in Romanian Language
• RoQLlama: A Lightweight Romanian Adapted Language Model