GUPEA >
Faculty of Humanities / Humanistiska fakulteten >
Department of Swedish / Institutionen för svenska språket >
Doctoral Theses / Doktorsavhandlingar Institutionen för svenska språket >

Splitting rocks: Learning word sense representations from corpora and lexica


Please use this identifier to cite or link to this item: http://hdl.handle.net/2077/60509

Files in This Item:

File Description SizeFormat
gupea_2077_60509_1.pdfThesis1299KbAdobe PDF
View/Open
gupea_2077_60509_2.pdfCover1616KbAdobe PDF
View/Open
gupea_2077_60509_3.pdfAbstract50KbAdobe PDF
View/Open
Title: Splitting rocks: Learning word sense representations from corpora and lexica
Authors: Nieto Piña, Luis
Issue Date: 23-Aug-2019
University: Göteborgs universitet. Humanistiska fakulteten
University of Gothenburg. Faculty of Arts
Institution: Department of Swedish ; Institutionen för svenska språket
Parts of work: Luis Nieto Piña and Richard Johansson 2015. A simple and efficient method to generate word sense representations. Proceedings of the International Conference Recent Advances in Natural Language Processing, 465–472. Hissar, Bulgaria.

Luis Nieto Piña and Richard Johansson 2016. Embedding senses for efficient graph-based word sense disambiguation. Proceedings of TextGraphs-10: the Workshop on Graph-based Methods for Natural Language Processing, NAACL-HLT 2016, 1–5. San Diego, USA.

Luis Nieto Piña and Richard Johansson 2017. Training word sense embeddings with lexicon-based regularization. Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Asian Federation of Natural Language Processing. Taipei, Taiwan.

Luis Nieto Piña and Richard Johansson 2018. Automatically Linking Lexical Resources with Word Sense Embedding Models. Proceedings of the third workshop on semantic deep learning (SemDeep-3), COLING 2018, 23–29. Association for Computational Linguistics. Santa Fe, USA.

Lars Borin, Luis Nieto Piña and Richard Johansson 2015. Here be dragons? The perils and promises of inter-resource lexical-semantic mapping. Proceedings of the workshop on semantic resources and semantic annotation for natural language processing and the digital humanities at NODALIDA 2015, 1–11. Vilnius, Lithuania.
Date of Defence: 2019-09-13
Disputation: Fredagen den 13 september 2019, kl. 13.15, Lilla hörsalen, Humanisten, Lundgrensgatan 1B
Degree: Doctor of Philosophy
Publication type: Doctoral thesis
Series/Report no.: Data Linguistica
30
Keywords: language technology
natural language processing
distributional models
semantic representations
distributed representations
word senses
embeddings
word sense disambiguation
linguistic resources
corpus
lexicon
machine learning
neural networks
Abstract: The representation of written language semantics is a central problem of language technology and a crucial component of many natural language processing applications, from part-of-speech tagging to text summarization. These representations of linguistic units, such as words or sentences, allow computer applications that work with language to process and manipulate the meaning of text. In particular, a family of models has been successfully developed based on automatically learning semantics from... more
ISBN: 978-91-87850-75-2
ISSN: 0347-948X
URI: http://hdl.handle.net/2077/60509
Appears in Collections:Doctoral Theses from University of Gothenburg / Doktorsavhandlingar från Göteborgs universitet
Doctoral Theses / Doktorsavhandlingar Institutionen för svenska språket

 

 

© Göteborgs universitet 2011