Back
Rossini_vanderPlas_2026_ACL_EACL
Conference paper (in proceedings)

Binary token-level classification with DeBERTa for all-type MWE identification : a lightweight approach with linguistic enhancement

  • Rossini, Diego ORCID Istituto di argomentazione, linguistica e semiotica (IALS), Facoltà di comunicazione, cultura e società, Università della Svizzera italiana, Svizzera
  • van der Plas, Marie Louise Elizabeth ORCID Istituto di argomentazione, linguistica e semiotica (IALS), Facoltà di comunicazione, cultura e società, Università della Svizzera italiana, Svizzera
  • 2026
Published in:
  • Findings of the Association for Computational Linguistics (EACL 2026). - 2026
MWE
NLP
Token Classification
English We present a comprehensive approach for multiword expression (MWE) identification that combines binary token-level classification, linguistic feature integration, and data augmentation. Our DeBERTa-v3-large model achieves 69.8% F1 on the CoAM dataset, surpassing the best results (Qwen-72B, 57.8% F1) on this dataset by 12 points while using 165x fewer parameters. We achieve this performance by (1) reformulating detection as binary token-level START/END/INSIDE classification rather than span-based prediction, (2) incorporating NP chunking and dependency features that help discontinuous and NOUN-type MWEs identification, and (3) applying oversampling that addresses severe class imbalance in the training data. We confirm the generalization of our method on the STREUSLE dataset, achieving 78.9% F1. These results demonstrate that carefully designed smaller models can substantially outperform LLMs on structured NLP tasks, with important implications for resource-constrained deployments.
Collections
Language
  • English
Classification
Language, linguistics
Other electronic version

published version

Notes
  • EACL 2026 – 17th Conference of the European Chapter of the Association for Computational Linguistics
  • Rabat, Morocco
  • March 24–29, 2026
License
CC BY
Open access status
gold
Identifiers
Persistent URL
https://n2t.net/ark:/12658/srd1335030
Statistics
Document views: 0 File downloads:
  • Rossini_vanderPlas_2026_ACL_EACL: 0