The Use of Clustering Techniques for Language Modeling - Application to Asian Languages

The Use of Clustering Techniques for Language Modeling - Application to Asian Languages

Cached

Download Links

by Jianfeng Gao , Joshua T. Goodman , Jiangbo Miao

Citations:

BibTeX

@MISC{Gao_theuse,
    author = {Jianfeng Gao and Joshua T. Goodman and Jiangbo Miao},
    title = {The Use of Clustering Techniques for Language Modeling - Application to Asian Languages},
    year = {}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

Cluster-based n-gram modeling is a variant of normal word-based n-gram modeling. It attempts to make use of the similarities between words. In this paper, we present an empirical study of clustering techniques for Asian language modeling. Clustering is used to improve the performance (i.e. perplexity) of language models as well as to compress language models. Experimental tests are presented for cluster-based trigram models on a Japanese newspaper corpus, and on a Chinese heterogeneous corpus.

Citations

649	A stochastic parts program and noun phrase parser for unrestricted text - Church - 1988
631	J: An Empirical Study of Smoothing Techniques for Language Modeling - SF, Goodman - 1996
574	Estimation of Probabilities from Sparse Data for the Language Model Component of a Speech Recognizer - Katz - 1987
540	Class-based n-gram models of natural language - Brown, Pietra, et al. - 1992
519	Scatter/gather: A cluster-based approach to browsing large document collections - Cutting, Pedersen, et al. - 1992
502	A statistical approach to machine translation - Brown, Cocke, et al. - 1990
477	Distributional clustering of English words - Pereira, Tishby, et al. - 1993
302	Self-Organized Language Modeling for Speech Recognition - Jelinek - 1990
158	A Hidden Markov Model Information Retrieval System - Miller, Leek, et al. - 1999
149	On structuring probabilistic dependencies in stochastic language modeling. Computer Speech and Language - Ney, Essen, et al. - 1994
91	Speech and language processing - Jurafsky, Martin - 2000
88	Entropy-based pruning of backoff language models - Stolcke - 1998
82	Improved Clustering Techniques for Class-Based Statistical Language Models - Kneser, Ney
63	A Spelling Correction Program Based on a Noisy Channel Model - Kernighan, Church, et al. - 1990
51	Scalable backoff language models - Seymore, Rosenfeld - 1996
40	Toward a unified approach to statistical language modeling for Chinese - Gao, Goodman, et al. - 2002
40	Estimation of Powerful Language Models from Small and Large Corpora - Placeway, Schwartz, et al. - 1993
28	Spoken language processing - Huang, Acero, et al. - 2001
28	Comparison of Part-of-speech and Automatically Derived Category-based Language Models for Speech Recognition - Niesler, Whittaker, et al. - 1998
19	A Novel Word Clustering Algorithm Based on Latent Semantic Analysis - Bellegarda, Butzberger, et al. - 1996
18	Statistical language modeling using a variable context length - Kneser - 1996
12	Multi-class composite n-gram based on connection direction - Yamamoto, Sagisaka - 1999
11	POS tags and decision trees for language modeling - Heeman - 1999
11	Navigating the Information Superhighway Using Spoken Language Interfaces - Zue - 1995
10	Incorporating POS Tagging into Language Modeling - Heeman, Allen - 1997
8	Flexible Use of Semantic Constraints in Speech Recognition - Ward, Young - 1993
6	Building class-based language models with contextual statistics - Bai, Li, et al. - 1998
6	Flexible parsing: CMU’s approach to spoken language understanding - Issar, Ward - 1994
6	An Automatic Technique to include Grammatical and Morphological Information in a Trigram2based Statistical Language Model - Maltese, Mancini - 1992
5	Phrase bracketing and annotating on Chinese language corpus - Zhou - 1996
4	Evaluation of a language model using a clustered model backoff - Miller, Alleva - 1997
2	A bit of progress in language modeling. Submitted to Computer Speech and Language. Draft available fromhttp://www.research.microsoft.com/~joshuago - Goodman - 2001
2	Tongyici Cilin. Shanghai Cishu - Mei - 1983
2	An intelligent and efficient word-class-based Chinese language model for Mandarin speech recognition with very large vocabulary - Yang - 1994
2	n1 Y = n + 2n n D1 = 1− 2Y n i (21) (22) (23) (24) n D2 = 2 − 3Y n n D3 = 3 − 4Y n where n1, n2, n3, andn4are total number of trigrams with exactly one, two, three, and four counts. Notice that for experiments in this paper, we do not use this approximati - Ries, K