Edition 1.1 of the PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions

Carlos Ramisch (1) , Silvio Cordeiro (1) , Agata Savary (2) , Veronika Vincze (3) , Verginica Barbu Mititelu (4) , Archna Bhatia (5) , Maja Buljan (6) , Marie Candito , Polona Gantar (7) , Voula Giouli (8) , Tunga Güngör (9) , Abdelati Hawwari (10) , Uxoa Iñurrieta (11) , Jolanta Kovalevskaitė (12) , Simon Krek (13) , Timm Lichte (14) , Chaya Liebeskind (15) , Johanna Monti (16) , Carla Parra Escartín (17) , Behrang Qasemizadeh (14) , Renata Ramisch (18) , Nathan Schneider (19) , Ivelina Stoyanova (20) , Ashwini Vaidya (21) , Abigail Walsh (17)

1 TALEP - Traitement Automatique du Langage Ecrit et Parlé
2 BDTLN - Bases de données et traitement des langues naturelles
3 University of Szeged [Szeged]
4 Romanian Academy
5 IHMC - Florida Institute for Human and Machine Cognition [Pensacola]
6 University of Stuttgart
7 University of Ljubljana
8 ATHENA - Research and Innovation Center in Information, Communication and Knowledge Technologies
9 Boǧaziçi üniversitesi = Boğaziçi University [Istanbul]
10 GW - The George Washington University
11 UPV / EHU - University of the Basque Country = Euskal Herriko Unibertsitatea
12 VDU - Vytautas Magnus University - Vytauto Didziojo Universitetas
13 IJS - Jozef Stefan Institute [Ljubljana]
14 Heinrich Heine Universität Düsseldorf = Heinrich Heine University [Düsseldorf]
15 JCT - Jerusalem College of Technology
16 UniOr - Università di Napoli L'Orientale = University of Naples
17 DCU - Dublin City University [Dublin]
18 Interinstitutional Center for Computational Linguistics
19 GU - Georgetown University [Washington]
20 BAS - Bulgarian Academy of Sciences
21 IIT Delhi - Indian Institute of Technology Delhi

This paper describes the PARSEME Shared Task 1.1 on automatic identification of verbal multi-word expressions. We present the annotation methodology, focusing on changes from last year's shared task. Novel aspects include enhanced annotation guidelines, additional annotated data for most languages, corpora for some new languages, and new evaluation settings. Corpora were created for 20 languages, which are also briefly discussed. We report organizational principles behind the shared task and the evaluation metrics employed for ranking. The 17 participating systems, their methods and obtained results are also presented and analysed.

Domaines: Informatique et langage [cs.CL]; Linguistique

Carlos Ramisch, Silvio Cordeiro, Agata Savary, Veronika Vincze, Verginica Barbu Mititelu, et al.. Edition 1.1 of the PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions. Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018), Aug 2018, Santa Fe, United States. pp.222 - 240. ⟨hal-01865575⟩