Related Researcher

Author's Photo

Jang, Gil-Jin
Machine Intelligence Lab
Research Interests
  • Acoustic signal processing
  • Computer vision
  • Biomedical signal processing


Minimum Discrimination Information-based Language Model Adaptation Using Tiny Domain Corpora for Intelligent Personal Assistants

DC Field Value Language Jang, Gil-Jin ko Kim, Saejoon ko Kim, Ji-Hwan ko 2014-04-10T02:17:55Z - 2013-06-12 ko 2012-11 -
dc.identifier.citation IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, v.58, no.4, pp.1359 - 1365 ko
dc.identifier.issn 0098-3063 ko
dc.identifier.uri -
dc.identifier.uri ko
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. ko
dc.description.statementofresponsibility close -
dc.language ENG ko
dc.subject Adaptation methods ko
dc.subject Conditional distribution ko
dc.subject Constraint estimation ko
dc.subject Discrete distribution ko
dc.subject Language model ko
dc.subject Language model adaptation ko
dc.subject Minimum discriminationinformation ko
dc.subject Personal assistants ko
dc.subject Relative performance ko
dc.subject Tiny domaincorpus ko
dc.subject Word frequencies ko
dc.subject Word similarity ko
dc.subject Wordnet ko
dc.title Minimum Discrimination Information-based Language Model Adaptation Using Tiny Domain Corpora for Intelligent Personal Assistants ko
dc.type ARTICLE ko
dc.identifier.scopusid 2-s2.0-84873878783 ko
dc.identifier.wosid 000314168700035 ko
dc.type.rims ART ko
dc.description.wostc 0 *
dc.description.scopustc 0 * 2015-02-28 * 2014-08-19 *
dc.identifier.doi 10.1109/TCE.2012.6415007 ko
Appears in Collections:
EE_Journal Papers

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show simple item record


  • mendeley


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