ACL RD-TEC 1.0 Summarization of J96-1001

Paper Title:
TRANSLATING COLLOCATIONS FOR BILINGUAL LEXICONS: A STATISTICAL APPROACH

Authors: Frank Smadja and Vasileios Hatzivassiloglou and Kathleen R. McKeown

Other assigned terms:

  • aligned corpus
  • alignment error rate
  • ambiguous words
  • american english
  • approach
  • argumentation
  • association for computational linguistics
  • bilingual corpora
  • bilingual corpus
  • bilingual dictionary
  • bilingual lexicon
  • bilingual lexicons
  • break
  • british english
  • candidate translation
  • case
  • co-occurrence
  • coefficient
  • collocation
  • community
  • complex sentence
  • compound noun
  • compounds
  • concepts
  • conditional probabilities
  • corpora
  • correlation
  • derivation
  • dice
  • dice coefficient
  • dictionary
  • disk
  • distribution
  • ellipsis
  • english corpus
  • english translation
  • entropy
  • error rate
  • estimation
  • evaluation methodology
  • evaluations
  • events
  • experimental results
  • fact
  • feature
  • french
  • french corpus
  • french translation
  • french word
  • generation
  • generative capacity
  • heuristic
  • human translation
  • implementation
  • index
  • inflected forms
  • interlingua
  • joint probability
  • knowledge
  • large corpus
  • lexical information
  • lexicography
  • lexicon
  • linear time
  • linguist
  • linguistics
  • literal translation
  • mapping
  • mathematical model
  • meaning
  • meanings
  • measure
  • measures
  • message
  • method
  • methodology
  • multilingual information
  • multiword expressions
  • mutual information
  • natural language
  • natural languages
  • noise
  • noun phrases
  • pairs of words
  • paragraphs
  • parallel bilingual corpus
  • parallel corpora
  • part-of-speech
  • part-of-speech information
  • phrase
  • polysemy
  • portability
  • precision
  • preposition
  • probabilities
  • probability
  • process
  • query
  • relation
  • representations
  • search query
  • search space
  • semantic
  • semantic features
  • semantic rules
  • sentence
  • sentences
  • similarity measure
  • similarity measures
  • similarity score
  • similarity scores
  • size of the corpus
  • source language
  • sparse data
  • statistical natural language
  • statistics
  • sublanguage
  • syntactic constituents
  • syntactic relation
  • target language
  • target languages
  • technical terminology
  • technique
  • technology
  • term
  • terms
  • text
  • text corpora
  • training
  • training corpora
  • training data
  • transcripts
  • translations
  • understanding
  • uniform distribution
  • user
  • verb
  • word
  • word collocation
  • word level
  • word order
  • word pair
  • word-by-word basis
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***