Multiword expression identification using deep learning

Simple item page
dc.contributor.advisorBhavsar, Virendrakumar
dc.contributor.advisorCook, Paul
dc.contributor.authorGharbieh, Waseem
dc.date.accessioned2023-03-01T16:53:09Z
dc.date.available2023-03-01T16:53:09Z
dc.date.issued2017
dc.date.updated2019-03-04T00:00:00Z
dc.description.abstractMultiword expressions combine words in various ways to produce phrases that have properties that are not predictable from the properties of their individual words or their normal mode of combination. There are many types of multiword expressions including proverbs, named entities, and verb noun combinations. In this thesis, we propose various deep learning models to identify multiword expressions and compare their performance to more traditional machine learning models and current multiword expression identification systems. We show that convolutional neural networks are able to perform better than state-of-the-art with the three hidden layer convolutional neural network performing best. To our knowledge, this is the first work that applies deep learning models for broad multiword expression identification.
dc.description.copyright© Waseem Gharbieh, 2017
dc.description.noteM.C.S. University of New Brunswick, Faculty of Computer Science, 2017.
dc.formattext/xml
dc.format.extentxiii, 102 pages
dc.format.mediumelectronic
dc.identifier.otherThesis 10015
dc.identifier.urihttps://unbscholar.lib.unb.ca/handle/1882/14615
dc.language.isoen_CA
dc.publisherUniversity of New Brunswick
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.subject.classificationDeep learning (Computer science)
dc.subject.classificationOpinion mining.
dc.subject.disciplineComputer Science
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshNatural language processing (Computer science)
dc.subject.lcshDiscourse analysis -- Data processing.
dc.subject.lcshComputational linguistics.
dc.subject.lcshMachine learning.
dc.subject.lcshIdioms -- Data processing.
dc.subject.lcshTerms and phrases -- Data processing.
dc.titleMultiword expression identification using deep learning
dc.typemaster thesis
thesis.degree.disciplineComputer Science
thesis.degree.fullnameMaster of Computer Science
thesis.degree.grantorUniversity of New Brunswick
thesis.degree.levelmasters
thesis.degree.nameM.C.S.

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
item.pdf
Size:
668.18 KB
Format:
Adobe Portable Document Format
Download

Collections

Open Theses & Dissertations