Abstract
This paper addresses the issue of multi-word expression (MWE) detection by employing a new decoding strategy inspired after graph-based parsing. We show that this architecture achieves state-of-the-art results with minimum feature-engineering, just by relying on lexicalized and morphological attributes. We validate our approach in a multilingual setting, using standard MWE corpora supplied in the PARSEME Shared Task.- Anthology ID:
- W18-4928
- Volume:
- Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018)
- Month:
- August
- Year:
- 2018
- Address:
- Santa Fe, New Mexico, USA
- Editors:
- Agata Savary, Carlos Ramisch, Jena D. Hwang, Nathan Schneider, Melanie Andresen, Sameer Pradhan, Miriam R. L. Petruck
- Venues:
- LAW | MWE
- SIGs:
- SIGLEX | SIGANN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 254–260
- Language:
- URL:
- https://aclanthology.org/W18-4928
- DOI:
- Cite (ACL):
- Tiberiu Boros and Ruxandra Burtica. 2018. GBD-NER at PARSEME Shared Task 2018: Multi-Word Expression Detection Using Bidirectional Long-Short-Term Memory Networks and Graph-Based Decoding. In Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018), pages 254–260, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
- Cite (Informal):
- GBD-NER at PARSEME Shared Task 2018: Multi-Word Expression Detection Using Bidirectional Long-Short-Term Memory Networks and Graph-Based Decoding (Boros & Burtica, LAW-MWE 2018)
- PDF:
- https://preview.aclanthology.org/naacl24-info/W18-4928.pdf