ACL RD-TEC 1.0 Summarization of P94-1010

Paper Title:
A STOCHASTIC FINITE-STATE WORD-SEGMENTATION ALGORITHM FOR CHINESE

Authors: Richard Sproat and Chilin Shih and William Gale and Nancy Chang

Other assigned terms:

  • abbreviation
  • affix
  • affixes
  • approach
  • arithmetic mean
  • backoff
  • backoff model
  • bias
  • bigram
  • case
  • chinese text
  • chinese word
  • class-based model
  • cluster
  • corpora
  • correlation
  • dictionary
  • dictionary entries
  • dictionary entry
  • distance matrix
  • essay
  • fact
  • foreign words
  • frame
  • heuristics
  • human performance
  • independence model
  • inter-human agreement
  • knowledge
  • lexical entries
  • lexical knowledge
  • lexicon
  • likelihood
  • linguistic
  • mappings
  • maximum likelihood estimate
  • meaning
  • measure
  • measures
  • method
  • morphological rules
  • names
  • nouns
  • part-of-speech
  • pause
  • personal names
  • plural noun
  • precision
  • precision measure
  • probabilities
  • probability
  • pronunciation
  • proper name
  • proper names
  • segmentation problem
  • segments
  • semantic
  • sentence
  • sentences
  • similarity matrix
  • similarity measures
  • singular noun
  • source language
  • statistical model
  • statistics
  • stems
  • suffix
  • suffixes
  • terms
  • test corpora
  • test corpus
  • text
  • tokens
  • transitive closure
  • unigram
  • unknown word model
  • verb
  • word
  • word corpus
  • word model
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***