Detection of agreement vs. disagreement in meetings: training with unlabeled data

  • Authors:
  • Dustin Hillard;Mari Ostendorf;Elizabeth Shriberg

  • Affiliations:
  • University of Washington, EE;University of Washington, EE;SRI International and ICSI

  • Venue:
  • NAACL-Short '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: companion volume of the Proceedings of HLT-NAACL 2003--short papers - Volume 2
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

To support summarization of automatically transcribed meetings, we introduce a classifier to recognize agreement or disagreement utterances, utilizing both word-based and prosodic cues. We show that hand-labeling efforts can be minimized by using unsupervised training on a large unlabeled data set combined with supervised training on a small amount of data. For ASR transcripts with over 45% WER, the system recovers nearly 80% of agree/disagree utterances with a confusion rate of only 3%.