uu.seUppsala universitets publikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association
  • 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
Bridge the gap between statistical and hand-crafted grammars
2013 (engelsk)Inngår i: Computer speech & language (Print), ISSN 0885-2308, E-ISSN 1095-8363, Vol. 27, nr 5, s. 1085-1104Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

LTAG is a rich formalism for performing NLP tasks such as semantic interpretation, parsing, machine translation and information retrieval. Depend on the specific NLP task, different kinds of LTAGs for a language may be developed. Each of these LTAGs is enriched with some specific features such as semantic representation and statistical information that make them suitable to be used in that task. The distribution of these capabilities among the LTAGs makes it difficult to get the benefit from all of them in NLP applications.

This paper discusses a statistical model to bridge between two kinds LTAGs for a natural language in order to benefit from the capabilities of both kinds. To do so, an HMM was trained that links an elementary tree sequence of a source LTAG onto an elementary tree sequence of a target LTAG. Training was performed by using the standard HMM training algorithm called Baum–Welch. To lead the training algorithm to a better solution, the initial state of the HMM was also trained by a novel EM-based semi-supervised bootstrapping algorithm.

The model was tested on two English LTAGs, XTAG (XTAG-Group, 2001) and MICA's grammar (Bangalore et al., 2009) as the target and source LTAGs, respectively. The empirical results confirm that the model can provide a satisfactory way for linking these LTAGs to share their capabilities together.

sted, utgiver, år, opplag, sider
2013. Vol. 27, nr 5, s. 1085-1104
HSV kategori
Identifikatorer
URN: urn:nbn:se:uu:diva-242750DOI: 10.1016/j.csl.2013.02.001OAI: oai:DiVA.org:uu-242750DiVA, id: diva2:784892
Tilgjengelig fra: 2015-01-31 Laget: 2015-01-31 Sist oppdatert: 2017-12-05bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekst

Personposter BETA

Basirat, Ali

Søk i DiVA

Av forfatter/redaktør
Basirat, Ali
I samme tidsskrift
Computer speech & language (Print)

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 430 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association
  • 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