Seen2Unseen at PARSEME Shared Task 2020: All Roads do not Lead to Unseen Verb-Noun VMWEs - Archive ouverte HAL Access content directly
Conference Papers Year :

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

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.
Fichier principal
Vignette du fichier
main.pdf (224.16 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-03014867 , version 1 (19-11-2020)

Identifiers

  • HAL Id : hal-03014867 , version 1

Cite

Caroline Pasquer, Agata Savary, Carlos Ramisch, Jean-Yves Antoine. Seen2Unseen at PARSEME Shared Task 2020: All Roads do not Lead to Unseen Verb-Noun VMWEs. Joint Workshop on Multiword Expressions and Electronic Lexicons (MWE-LZX 2020), 2020, Barcelona, Spain. ⟨hal-03014867⟩
32 View
52 Download

Share

Gmail Facebook Twitter LinkedIn More