Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
Extractive summarization of multi-party meetings through discourse segmentation
Bokaei, M. H ; Sharif University of Technology | 2016
557
Viewed
- Type of Document: Article
- DOI: 10.1017/S1351324914000199
- Publisher: Cambridge University Press , 2016
- Abstract:
- In this article we tackle the problem of multi-party conversation summarization. We investigate the role of discourse segmentation of a conversation on meeting summarization. First, an unsupervised function segmentation algorithm is proposed to segment the transcript into functionally coherent parts, such as Monologuei (which indicates a segment where speaker i is the dominant speaker, e.g., lecturing all the other participants) or Discussionx1x2,...,xn (which indicates a segment where speakers x 1 to xn involve in a discussion). Then the salience score for a sentence is computed by leveraging the score of the segment containing the sentence. Performance of our proposed segmentation and summarization algorithms is evaluated using the AMI meeting corpus. We show better summarization performance over other state-of-the-art algorithms according to different metrics
- Keywords:
- Artificial intelligence ; AMI Meetings ; Discourse segmentation ; Extractive summarizations ; Multi-party conversations ; Segmentation algorithms ; State-of-the-art algorithms ; Software engineering
- Source: Natural Language Engineering ; Volume 22, Issue 1 , 2016 , Pages 41-72 ; 13513249 (ISSN)
- URL: http://ieeexplore.ieee.org/document/7501601