Afficher la couverture 'Seen2Unseen at PARSEME Shared Task 2020: All Roads do not Lead to Unseen Verb-Noun VMWEs | Pasquer, Caroline' en grand format
/5

0 avis

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

Archive ouverte

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

Edité par CCSD -

International audience. 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.

Suggestions

Du même auteur

Advances in Multiword Expression Identification for the Italian language: The PARSEME shared task edition 1.1

Archive ouverte | Monti, Johanna | CCSD

International audience. EThis contribution describes the results of the second edition of the shared task on automatic identification of verbalmultiword expressions, organized as part of the LAW-MWE-CxG 2018 worksho...

PARSEME corpus release 1.3

Archive ouverte | Savary, Agata | CCSD

International audience

UniDive: A COST Action on Universality, Diversity and Idiosyncrasy in Language Technology

Archive ouverte | Savary, Agata | CCSD

International audience. This paper presents the objectives, organization and activities of the UniDive COST Action, a scientific network dedicated to universality, diversity and idiosyncrasy in language technology. ...

Chargement des enrichissements...