Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Evaluating Globally Normalized Transition Based Neural Networks for Multilingual Natural Language Understanding
KTH, School of Computer Science and Communication (CSC).
2017 (English)Independent thesis Advanced level (degree of Master (Two Years)), 300 HE creditsStudent thesis
Abstract [en]

We analyze globally normalized transition-based neural network models for dependency parsing on English, German, Spanish, and Catalan. We compare the results with FreeLing, an open source language analysis tool developed at the UPC natural language processing research group. Furthermore we study how the mini-batch size, the number of units in the hidden layers and the beam width affect the performances of the network. Finally we propose a multi-lingual parser with parameters sharing and experiment with German and English obtaining a significant accuracy improvement upon the monolingual parsers. These multi-lingual parsers can be used for low-resource languages of for all the applications with low memory requirements, where having one model per language in intractable. 

Place, publisher, year, edition, pages
2017. , 51 p.
Keyword [en]
nlp, machine learning, dependency parsing
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-208303OAI: oai:DiVA.org:kth-208303DiVA: diva2:1105281
External cooperation
Polytechnic University of Catalonia
Educational program
Master of Science in Engineering - Computer Science and Technology
Supervisors
Examiners
Available from: 2017-06-05 Created: 2017-06-02 Last updated: 2017-06-05Bibliographically approved

Open Access in DiVA

fulltext(2181 kB)20 downloads
File information
File name FULLTEXT01.pdfFile size 2181 kBChecksum SHA-512
bfb85f82569f1039146dcadf7f095cddfb13febefcdd1220bdb723b5a9eaf040368677e91a307cad2a9befc1b0bbf8ca687afb647abf3fd9437c85e1d79e0af4
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 20 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 105 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf