Paper: Detection of Agreement and Disagreement in Broadcast Conversations

ACL ID P11-2065
Title Detection of Agreement and Disagreement in Broadcast Conversations
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

We present Conditional Random Fields based approaches for detecting agree- ment/disagreement between speakers in English broadcast conversation shows. We develop annotation approaches for a variety of linguistic phenomena. Various lexical, structural, durational, and prosodic features are explored. We compare the performance when using features extracted from au- tomatically generated annotations against that when using human annotations. We investigate the efficacy of adding prosodic features on top of lexical, structural, and durational features. Since the training data is highly imbalanced, we explore two sam- pling approaches, random downsampling and ensemble downsampling. Overall, our approach achieves 79.2% (precision), 50.5% (recall), 61.7% (F1) for agreement detection and 69.2% (pr...