File Download

There are no files associated with this item.

  • Find it @ UNIST can give you direct access to the published full text of this article. (UNISTARs only)

Views & Downloads

Detailed Information

Cited time in webofscience Cited time in scopus
Metadata Downloads

Full metadata record

DC Field Value Language
dc.citation.endPage 1365 -
dc.citation.number 4 -
dc.citation.startPage 1359 -
dc.citation.title IEEE TRANSACTIONS ON CONSUMER ELECTRONICS -
dc.citation.volume 58 -
dc.contributor.author Jang, Gil-Jin -
dc.contributor.author Kim, Saejoon -
dc.contributor.author Kim, Ji-Hwan -
dc.date.accessioned 2023-12-22T04:38:35Z -
dc.date.available 2023-12-22T04:38:35Z -
dc.date.created 2013-06-12 -
dc.date.issued 2012-11 -
dc.description.abstract This paper proposes a novel Language Model (LM) adaptation method based on Minimum Discrimination Information (MDI). In the proposed method, a background LM is viewed as a discrete distribution and an adapted LM is built to be as close as possible to the background LM, while satisfying unigram constraint. This is due to the fact that there is a limited amount of domain corpus available for the adaptation of a natural language-based intelligent personal assistant system. Two unigram constraint estimation methods are proposed: one based on word frequency in the domain corpus, and one based on word similarity estimated from WordNet. In terms of the adapted LM's perplexity using word frequency in tiny domain corpora (ranging from 30 similar to 120 seconds in length) the relative performance improvements are measured at 13.9%similar to 16.6%. Further relative performance improvements (1.5%similar to 2.4%) are observed when WordNet is used to generate word similarities. These successes express an efficient ways for re-scaling and normalizing the conditional distribution, which uses an interpolation-based LM1. -
dc.identifier.bibliographicCitation IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, v.58, no.4, pp.1359 - 1365 -
dc.identifier.doi 10.1109/TCE.2012.6415007 -
dc.identifier.issn 0098-3063 -
dc.identifier.scopusid 2-s2.0-84873878783 -
dc.identifier.uri https://scholarworks.unist.ac.kr/handle/201301/3678 -
dc.identifier.url http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84873878783 -
dc.identifier.wosid 000314168700035 -
dc.language 영어 -
dc.publisher IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC -
dc.title Minimum Discrimination Information-based Language Model Adaptation Using Tiny Domain Corpora for Intelligent Personal Assistants -
dc.type Article -
dc.relation.journalWebOfScienceCategory Engineering, Electrical & Electronic; Telecommunications -
dc.relation.journalResearchArea Engineering; Telecommunications -
dc.description.journalRegisteredClass scie -
dc.description.journalRegisteredClass scopus -
dc.subject.keywordAuthor Language model adaptation -
dc.subject.keywordAuthor Tiny domain corpus -
dc.subject.keywordAuthor Constraint estimation -
dc.subject.keywordAuthor Minimum discrimination information -

qrcode

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.