ACL RD-TEC 1.0 Summarization of C04-1007

Paper Title:
COMBINING HIERARCHICAL CLUSTERING AND MACHINE LEARNING TO PREDICT HIGH-LEVEL DISCOURSE STRUCTURE

Authors: Caroline Sporleder and Alex Lascarides

Other assigned terms:

  • adjective
  • adverb
  • ambiguity
  • analyser
  • anaphor
  • anaphora
  • anaphors
  • approach
  • boundary information
  • break
  • case
  • characters
  • co-occurrence
  • co-reference
  • cohesion
  • compound noun
  • cue phrase
  • cue phrases
  • data set
  • discourse
  • discourse segment
  • discourse structure
  • discourse tree
  • discourse treebank
  • distribution
  • entropy
  • f-score
  • fact
  • feature
  • feature set
  • feature sets
  • human performance
  • hypernym
  • hyponym
  • implementation
  • inter-paragraph relation
  • inter-paragraph structure
  • lexeme
  • lexical chain
  • lexical chains
  • lexical cohesion
  • likelihood
  • mapping
  • maps
  • mark-up
  • measure
  • measures
  • method
  • noun phrase
  • nouns
  • paragraph
  • paragraphs
  • parse
  • part-of-speech
  • part-of-speech information
  • penn discourse treebank
  • penn treebank
  • phrase
  • precision
  • probability
  • probability distribution
  • proper noun
  • proper noun chain
  • punctuation
  • punctuation mark
  • regular expressions
  • relation
  • rhetorical relations
  • rhetorical structure
  • rhetorical structure theory
  • rst discourse treebank
  • segments
  • semantic
  • semantic relatedness
  • semantic relation
  • sentence
  • sentence boundary
  • sentences
  • synonym
  • tagged text
  • term
  • test set
  • text
  • theory
  • trained model
  • training
  • training example
  • training examples
  • training set
  • tree
  • treebank
  • treebank project
  • trees
  • verb
  • word
  • word co-occurrence
  • word features
  • word sense
  • wordnet
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***