ACL RD-TEC 1.0 Summarization of A00-1027

Paper Title:
COMPOUND NOUN SEGMENTATION BASED ON LEXICAL DATA EXTRACTED FROM CORPUS

Other assigned terms:

  • adverb
  • agglutinative language
  • ambiguity
  • ambiguous words
  • annotated corpus
  • approach
  • baseline performance
  • bigram
  • bottom-up strategy
  • case
  • characters
  • composition
  • compound noun
  • compounds
  • content words
  • dictionary
  • distribution
  • eojeol corpus
  • experimental results
  • foreign word
  • frequency distribution
  • function word
  • generation
  • gold standard
  • gold standard test
  • interpretation
  • knowledge
  • korean compound noun
  • korean language
  • large corpus
  • lexical information
  • lexical knowledge
  • likelihood
  • meaning
  • meanings
  • method
  • methodology
  • morphological ambiguity
  • n-gram
  • n-gram model
  • names
  • natural language
  • nominals
  • nouns
  • parameter space
  • part of speech
  • parts of speech
  • personal names
  • phrase
  • precision
  • probability
  • probability model
  • procedure
  • process
  • pronoun
  • proper noun
  • query
  • seed
  • segmentation accuracy
  • segmentation dictionary
  • semantic
  • semantic information
  • semantic knowledge
  • sentence
  • statistical data
  • style
  • suffix
  • suffixes
  • syllables
  • syntactic unit
  • system performance
  • tagged corpus
  • technology
  • telecommunications research
  • terms
  • test set
  • training
  • training data
  • transition probability
  • trigram
  • user
  • verb
  • word
  • word corpus
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***