Class-Based n-gram Models of Natural Language

DMCA

Class-Based n-gram Models of Natural Language (1992)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Peter F. Brown , Peter V. deSouza , Robert L. Mercer , Vincent J. Della Pietra , Jenifer C. Lai

Venue:	Computational Linguistics
Citations:	986 - 5 self

BibTeX

@ARTICLE{Brown92class-basedn-gram,
    author = {Peter F. Brown and Peter V. deSouza and Robert L. Mercer and Vincent J. Della Pietra and Jenifer C. Lai},
    title = {Class-Based n-gram Models of Natural Language},
    journal = {Computational Linguistics},
    year = {1992},
    volume = {18},
    pages = {467--479}
}

OpenURL

Abstract

We address the problem of predicting a word from previous words in a sample of text. In particular we discuss n-gram models based on calsses of words. We also discuss several statistical algoirthms for assigning words to classes based on the frequency of their co-occurrence with other words. We find that we are able to extract classes that have the flavor of either syntactically based groupings or semantically based groupings, depending on the nature of the underlying statistics.

Keyphrases

class-based n-gram model natural language n-gram model underlying statistic previous word several statistical algoirthms

DMCA