ACL RD-TEC 1.0 Summarization of P06-1003

Paper Title:
UNSUPERVISED TOPIC MODELLING FOR MULTI-PARTY SPOKEN DISCOURSE

Authors: Matthew Purver and Konrad P. Körding and Thomas L. Griffiths and Joshua B. Tenenbaum

Other assigned terms:

  • annotation
  • approach
  • asr output
  • association for computational linguistics
  • bayesian model
  • benchmark
  • bigram
  • break
  • broadcast news
  • coherence
  • cohesion
  • conditional probabilities
  • conditional probability
  • correlation
  • cue phrases
  • dependency structure
  • dirichlet distribution
  • discourse
  • discourse information
  • distribution
  • document
  • events
  • fact
  • generative model
  • generative models
  • hierarchical structure
  • hmm model
  • hypotheses
  • icsi meeting corpus
  • joint distribution
  • knowledge
  • lexical cohesion
  • lexical information
  • lexical model
  • linear combination
  • linguistics
  • markov chain
  • measure
  • measures
  • meeting corpus
  • method
  • monologue
  • multi-party discourse
  • multinomial distribution
  • named entities
  • noise
  • paragraphs
  • posterior
  • posterior distribution
  • posterior probability
  • probabilities
  • probability
  • probability distribution
  • pronouns
  • prosody
  • recognition errors
  • segment boundaries
  • segment boundary
  • segmentation accuracy
  • segmentation problem
  • segments
  • semantic
  • semantic coherence
  • speech recognition errors
  • style
  • technique
  • terms
  • text
  • tokens
  • topics
  • training
  • transcriptions
  • transcripts
  • understanding
  • user
  • utterance
  • vocabulary
  • word
  • word error rates
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***