ERMI at PARSEME Shared Task 2020: Embedding-Rich Multiword Expression Identification

Zeynep Yirmibeşoğlu, Tunga Güngör


Abstract
This paper describes the ERMI system submitted to the closed track of the PARSEME shared task 2020 on automatic identification of verbal multiword expressions (VMWEs). ERMI is an embedding-rich bidirectional LSTM-CRF model, which takes into account the embeddings of the word, its POS tag, dependency relation, and its head word. The results are reported for 14 languages, where the system is ranked 1st in the general cross-lingual ranking of the closed track systems, according to the Unseen MWE-based F1.
Anthology ID:
2020.mwe-1.17
Volume:
Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons
Month:
December
Year:
2020
Address:
online
Editors:
Stella Markantonatou, John McCrae, Jelena Mitrović, Carole Tiberius, Carlos Ramisch, Ashwini Vaidya, Petya Osenova, Agata Savary
Venue:
MWE
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
130–135
Language:
URL:
https://aclanthology.org/2020.mwe-1.17
DOI:
Bibkey:
Cite (ACL):
Zeynep Yirmibeşoğlu and Tunga Güngör. 2020. ERMI at PARSEME Shared Task 2020: Embedding-Rich Multiword Expression Identification. In Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons, pages 130–135, online. Association for Computational Linguistics.
Cite (Informal):
ERMI at PARSEME Shared Task 2020: Embedding-Rich Multiword Expression Identification (Yirmibeşoğlu & Güngör, MWE 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.mwe-1.17.pdf