UNIGE document Chapitre d'actes
previous document  unige:99249  next document
add to browser collection
Title

Parsing and MWE Detection: Fips at the PARSEME Shared Task

Authors
Published in Stella Markantonatou, Carlos Ramisch,vAgata Savary, Veronika Vincze. Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017). Valencia, Spain - April, 2017 - Association for Computational Linguistics. 2017, p. 54-59
Abstract Identifying multiword expressions (MWEs) in a sentence in order to ensure their proper processing in subsequent applications, like machine translation, and performing the syntactic analysis of the sentence are interrelated processes. In our approach, priority is given to parsing alternatives involving collocations, and hence collocational information helps the parser through the maze of alternatives, with the aim to lead to substantial improvements in the performance of both tasks (collocation identification and parsing), and in that of a subsequent task (machine translation). In this paper, we are going to present our system and the procedure that we have followed in order to participate to the open track of the PARSEME shared task on automatic identification of verbal multiword expressions (VMWEs) in running texts.
Keywords Verbal multiword expressionsVMWECollocationCollocation identificationVMWE identificationPARSEME shared taskParserDeep parserFips
Full text
Structures
Research group Laboratoire d'Analyse et de Traitement du Langage (LATL)
Project PARSEME
Citation
(ISO format)
FOUFI, Vasiliki, NERIMA, Luka, WEHRLI, Eric. Parsing and MWE Detection: Fips at the PARSEME Shared Task. In: Stella Markantonatou, Carlos Ramisch,vAgata Savary, Veronika Vincze (Ed.). Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017). Valencia, Spain. [s.l.] : Association for Computational Linguistics, 2017. p. 54-59. https://archive-ouverte.unige.ch/unige:99249

64 hits

12 downloads

Update

Deposited on : 2017-11-20

Export document
Format :
Citation style :