lnu.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Tree Transformations in Inductive Dependency Parsing
Växjö universitet, Fakulteten för matematik/naturvetenskap/teknik, Matematiska och systemtekniska institutionen.
2007 (engelsk)Licentiatavhandling, monografi (Annet vitenskapelig)
Abstract [en]

This licentiate thesis deals with automatic syntactic analysis, or parsing, of natural languages. A parser constructs the syntactic analysis, which it learns by looking at correctly analyzed sentences, known as training data. The general topic concerns manipulations of the training data in order to improve the parsing accuracy.

Several studies using constituency-based theories for natural languages in such automatic and data-driven syntactic parsing have shown that training data, annotated according to a linguistic theory, often needs to be adapted in various ways in order to achieve an adequate, automatic analysis. A linguistically sound constituent structure is not necessarily well-suited for learning and parsing using existing data-driven methods. Modifications to the constituency-based trees in the training data, and corresponding modifications to the parser output, have successfully been applied to increase the parser accuracy. The topic of this thesis is to investigate whether similar modifications in the form of tree transformations to training data, annotated with dependency-based structures, can improve accuracy for data-driven dependency parsers. In order to do this, two types of tree transformations are in focus in this thesis.

The first one concerns non-projectivity. The full potential of dependency parsing can only be realized if non-projective constructions are allowed, which pose a problem for projective dependency parsers. On the other hand, non-projective parsers tend, among other things, to be slower. In order to maintain the benefits of projective parsing, a tree transformation technique to recover non-projectivity while using a projective parser is presented here.

The second type of transformation concerns linguistic phenomena that are possible but hard for a parser to learn, given a certain choice of dependency analysis. This study has concentrated on two such phenomena, coordination and verb groups, for which tree transformations are applied in order to improve parsing accuracy, in case the original structure does not coincide with a structure that is easy to learn.

Empirical evaluations are performed using treebank data from various languages, and using more than one dependency parser. The results show that the benefit of these tree transformations used in preprocessing and postprocessing to a large extent is language, treebank and parser independent.

sted, utgiver, år, opplag, sider
Växjö: Matematiska och systemtekniska institutionen , 2007. , s. 84
Serie
Rapporter från MSI, ISSN 1650-2647 ; 07002
Emneord [en]
Inductive Dependency Parsing, Dependency Structure, Tree Transformation, Non-projectivity, Coordination, Verb Group
HSV kategori
Forskningsprogram
Data- och informationsvetenskap
Identifikatorer
URN: urn:nbn:se:vxu:diva-1206OAI: oai:DiVA.org:vxu-1206DiVA, id: diva2:204999
Presentation
2007-01-19, D1136, D-byggnaden, Växjö Universitet, Växjö, 13:15 (engelsk)
Opponent
Veileder
Tilgjengelig fra: 2007-03-21 Laget: 2007-03-21 Sist oppdatert: 2018-01-13bibliografisk kontrollert

Open Access i DiVA

fulltekst(798 kB)413 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 798 kBChecksum MD5
8c59c83c4b754b2352f8499844e0dfabd1bf1cb0d4fce876c078467a3bc4d7fca7d906d9
Type fulltextMimetype application/pdf

Personposter BETA

Nilsson, Jens

Søk i DiVA

Av forfatter/redaktør
Nilsson, Jens
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 413 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 270 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf