Identification of multiword expressions: A fresh look at modelling and evaluation

Taslimipoor, Shiva; Rohanian, Omid; Mitkov, Ruslan; Fazly, Afsaneh

dc.contributor.author	Taslimipoor, Shiva
dc.contributor.author	Rohanian, Omid
dc.contributor.author	Mitkov, Ruslan
dc.contributor.author	Fazly, Afsaneh
dc.contributor.editor	Markantonatou, Stella
dc.contributor.editor	Ramisch, Carlos
dc.contributor.editor	Savary, Agata
dc.contributor.editor	Vincze, Veronika
dc.date.accessioned	2019-01-18T12:15:11Z
dc.date.available	2019-01-18T12:15:11Z
dc.date.issued	2018-10-25
dc.identifier.citation	Shiva Taslimipoor, Omid Rohanian, Ruslan Mitkov & Afsaneh Fazly. 2018. Identification of multiword expressions: A fresh look at modelling and evaluation. In Stella Markantonatou, Carlos Ramisch, Agata Savary & Veronika Vincze (eds.), Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop, 299– 317. Berlin: Language Science Press. DOI:10.5281/zenodo.1469569	en
dc.identifier.isbn	9783961101245
dc.identifier.doi	10.5281/zenodo.1469569
dc.identifier.uri	http://hdl.handle.net/2436/622066
dc.description	Automatic identification of Multiword Expressions (MWEs) in running text has recently received much attention among researchers in computational linguistics. The wide range of reported results for the task in the literature has prompted us to take a closer look at the algorithms and evaluation methods. For supervised classification of Verb+Noun expressions, we propose a context-based methodology in which we find word embeddings to be appropriate features. We discuss the importance of train and test splitting in validating the results and present type-aware train and test splitting. Given our specialised data, we also discuss the benefits of framing the task as classification rather than tagging.	en
dc.language.iso	en	en
dc.publisher	Language Science Press	en
dc.relation.url	http://langsci-press.org/catalog/book/204	en
dc.rights	Attribution-NonCommercial-NoDerivs 3.0 United States	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.subject	natural language processing	en
dc.subject	multiword expressions	en
dc.subject	idiomatic expressions	en
dc.title	Identification of multiword expressions: A fresh look at modelling and evaluation	en
dc.type	Chapter in book
pubs.edition	1
pubs.place-of-publication	Berlin, Germany
rioxxterms.licenseref.uri	https://creativecommons.org/licenses/by/4.0/
dc.source.booktitle	Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop
dc.source.beginpage	299
dc.source.endpage	318
refterms.dateFOA	2019-01-18T12:18:01Z