mlsanityData to 14 Oct 2026

Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition

arXiv 2304.11350 ↗First posted 22 Apr 2023cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 11 of its 25 references that are in the map. First posted on arXiv 22 Apr 2023.

Builds on

11 of 25 references.

References · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  5. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  6. 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
  7. 2020Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networkscited by 59
  8. 2020The birth of Romanian BERTcited by 44
  9. 2021Distilling the Knowledge of Romanian BERTs Using Multiple Teacherscited by 13
  10. 2020MTLB-STRUCT @PARSEME 2020: Capturing Unseen Multiword Expressions Using Multi-task Learning and Pre-trained Masked Language Modelscited by 6
  11. 2019Adversarial Training for Multilingual Acoustic Modelingcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 3.

4 papers.

  1. 2023Multilingual Multiword Expression Identification Using Lateral Inhibition and Domain Adaptationcited by 2
  2. 2025UniBERT: Adversarial Training for Language-Universal Representationscited by 0
  3. 2025Attention on Multiword Expressions: A Multilingual Study of BERT-based Models with Regard to Idiomaticity and Microsyntaxcited by 0
  4. 2025It's Not a Walk in the Park! Challenges of Idiom Translation in Speech-to-text Systemscited by 0