Seen2Unseen at PARSEME Shared Task 2020: All Roads do not Lead to Unseen Verb-Noun VMWEs

Caroline Pasquer, Agata Savary, Carlos Ramisch, Jean-Yves Antoine


Abstract
We describe the Seen2Unseen system that participated in edition 1.2 of the PARSEME shared task on automatic identification of verbal multiword expressions (VMWEs). The identification of VMWEs that do not appear in the provided training corpora (called unseen VMWEs) – with a focus here on verb-noun VMWEs – is based on mutual information and lexical substitution or translation of seen VMWEs. We present the architecture of the system, report results for 14 languages, and propose an error analysis.
Anthology ID:
2020.mwe-1.16
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:
124–129
Language:
URL:
https://aclanthology.org/2020.mwe-1.16
DOI:
Bibkey:
Cite (ACL):
Caroline Pasquer, Agata Savary, Carlos Ramisch, and Jean-Yves Antoine. 2020. Seen2Unseen at PARSEME Shared Task 2020: All Roads do not Lead to Unseen Verb-Noun VMWEs. In Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons, pages 124–129, online. Association for Computational Linguistics.
Cite (Informal):
Seen2Unseen at PARSEME Shared Task 2020: All Roads do not Lead to Unseen Verb-Noun VMWEs (Pasquer et al., MWE 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.mwe-1.16.pdf