ACL RD-TEC 1.0 Summarization of P06-1010

Paper Title:
NAMED ENTITY TRANSLITERATION WITH COMPARABLE CORPORA

Authors: Richard Sproat and Tao Tao and ChengXiang Zhai

Other assigned terms:

  • approach
  • association for computational linguistics
  • character sequence
  • characters
  • chinese named-entity
  • cluster
  • co-occurrence
  • co-occurrence relation
  • coefficient
  • comparable corpora
  • corpora
  • correlation
  • correlation coefficient
  • correlations
  • dictionaries
  • dictionary
  • distribution
  • document
  • english language
  • english phone string
  • english text
  • english-chinese corpus
  • estimation
  • fact
  • frequency correlation
  • frequency distribution
  • generation
  • good-turing estimation
  • hindi
  • interpolation
  • jensen-shannon divergence
  • language pairs
  • linguistics
  • measure
  • measures
  • method
  • mutual information
  • n-grams
  • named entities
  • named entity
  • named-entity
  • names
  • noise
  • pagerank
  • pearson correlation coefficient
  • pinyin
  • probabilities
  • probability
  • process
  • pronunciation
  • relation
  • russian
  • similarity measures
  • source-channel model
  • syllables
  • technique
  • terms
  • test set
  • text
  • text documents
  • tone
  • toolkit
  • topics
  • topology
  • training
  • training data
  • transition probabilities
  • translations
  • transliteration candidate
  • web pages
  • word
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***