Detection Of Agreement vs. Disagreement In Meetings: Training With Unlabeled Data

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%.

• Type: Conference
• Year: 2003
• Where: NAACL
• Authors: Dustin Hillard, Mari Ostendorf, Elizabeth Shriberg
• Keywords: Disagreement Utterances, Large Unlabeled Data, NAACL 2003, NAACL 2007, Prosodic Cues