Automatic N-gram Language Model Creation from Web Resources


NAIST \| Library	Advanced Search	Japanese \| English

Please use this identifier to cite or link to this item: http://hdl.handle.net/10061/7955

Title:	Automatic N-gram Language Model Creation from Web Resources
Authors:	Ryuichi Nishimura Kumiko Komatsu Yuka Kuroda Kentaro Nagatomo Akinobu Lee Hiroshi Saruwatari Kiyohiro Shikano
Issue Date:	Sep-2001
Start page:	2127
End page:	2130
Abstract:	This paper describes an automatic building of N-gram language models from Web texts for large vocabulary continuous speech recognition. Although a huge amount of well-formed texts are needed to train a model, collecting and organizing such text corpus for every task by hand needs a great labor. We need the language model to update frequently to cover the current topics. To deal with this problem, we propose an automatic language model creation method by collecting Web texts via keyword-based Web search engines. We can build a task-dependent language model by selecting suitable keywords for the task. A text filtering algorithm based on character perplexity is developed to extract proper Japanese texts from Web texts. A language model for a medical consulting task created by the proposed method shows the higher word recognition rate by 11.4% than that of a conventional newspaper language model.
Description:	EUROSPEECH2001: the 7th European Conference on Speech Communication and Technology, September 3-7, 2001, Aalborg, Denmark.
URI:	http://hdl.handle.net/10061/7955
ISSN:	1018-4074
Rights:	Copyright 2001 ISCA
Text Version:	Publisher
Appears in Collections:	情報科学研究科 / Graduate School of Information Science

Files in This Item:

File	Size	Format
EUROSPEECH_2001_2127.pdf	623.48 kB	Adobe PDF	View/Open