Task adaptation using map estimation in N-gram language modeling

Hirokazu Masataki, Yoshinori Sagisaka, Kazuya Hisaki, Tatsuya Kawahara

Research output: Contribution to journalConference article

21 Citations (Scopus)

Abstract

This paper describes a method of task adaptation in N-gram language modeling, for accurately estimating the N-gram statistics from the small amount of data of the target task. Assuming a task-independent N-gram to be a-priori knowledge, the N-gram is adapted to a target task by MAP (maximum a-posteriori probability) estimation. Experimental results showed that the perplexities of the task adapted models were 15% (trigram), 24% (bigram) lower than those of the task-independent model, and that the perplexity reduction of the adaptation went up to 39% at maximum when the amount of text data in the adapted task was very small.

Original languageEnglish
Pages (from-to)783-786
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2
Publication statusPublished - 1997 Jan 1
Externally publishedYes
EventProceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5) - Munich, Ger
Duration: 1997 Apr 211997 Apr 24

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Task adaptation using map estimation in N-gram language modeling'. Together they form a unique fingerprint.

  • Cite this