Extracting question/answer pairs in multi-party meetings

Understanding multi-party meetings involves tasks such as dialog act segmentation and tagging, action item extraction, and summarization. In this paper we introduce a new task for multi-party meetings: extracting question/answer pairs. This is a practical application for further processing such as summarization. We propose a method based on discriminative classi cation of individual sentences as questions and answers via lexical, speaker, and dialog act tag information, followed by a contextual optimization via Markov models. Our results indicate that it is possible to outperform a nontrivial baseline using dialog act tag information. More speci cally, our method achieves a 13% relative improvement over the baseline for the task of detecting answers in meetings.

• Type: Conference
• Year: 2008
• Where: ICASSP
• Authors: Andreas Kathol, Gökhan Tür
• Keywords: Dialog Act, Dialog Act Tag, ICASSP 2008, Multi-party Meetings, Signal Processing