Two decades of statistical language modeling: Where do we go from here?

被引：281

作者：

Rosenfeld, R ^{[1
]}

机构：

[1] Carnegie Mellon Univ, Sch Comp Sci, Pittsburgh, PA 15213 USA

来源：

PROCEEDINGS OF THE IEEE | 2000年 / 88卷 / 08期

关键词：

natural language processing; natural language technologies; statistical language modeling;

D O I：

10.1109/5.880083

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Statistical language models estimate the distribution of various natural language phenomena;for the purpose of speech recognition and other language technologies. Since the first significant model was proposed in 1980, many attempts have been made to improve the state-of-the-art. We review them here, point to a few promising directions, and argue for a Bayesian approach to integration of linguistic theories with data.

引用

页码：1270 / 1278

页数：9

共 85 条

[11]

BRILL E, 1998, P 36 ANN M ACL

[12]

Brown P. F., 1992, Computational Linguistics, V18, P467

[13]

Brown P. F., 1990, Computational Linguistics, V16, P79

[14]

BROWN PF, 1991, LANGUAGE MODELING US

[15]

BROWN R, 1995, P 6 INT C THEOR METH, P221

[16]

CARROL G, 1992, 9216 BROWN U COMP SC

[17]

CHELBA C, 1997, P 5 EUR C SPEECH COM, V5, P2775

[18]

Chelba C., 1999, P EUROSPEECH, V4, P1567

[19] A survey of smoothing techniques for ME models [J].

Chen, SF ;

Rosenfeld, R .

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2000, 8 (01) :37-50

[20]

CHEN SF, 1998, P ICASSP 98 SEATTL W

← 1 2 3 4 5 6 7 8 9 →