Identification of multiword expressions: A fresh look at modelling and evaluation
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.1469569Publisher
Language Science PressAdditional Links
http://langsci-press.org/catalog/book/204Type
Book chapterLanguage
enDescription
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.ISBN
3961101248The following license files are associated with this item:
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivs 3.0 United States