Role recognition for meeting participants: an approach based on lexical information and social network analysis
Lists
Only you see this
Abstract
This paper presents experiments on the automatic recognition of roles in meetings. The proposed approach combines two sources of information: the lexical choices made by people playing different roles on one hand, and the Social Networks describing the interactions between the meeting participants on the other hand. Both sources lead to role recognition results significantly higher than chance when used separately, but the best results are obtained with their combination. Preliminary experiments obtained over a corpus of 138 meeting recordings (over 45 hours of material) show that around 70% of the time is labeled correctly in terms of role.
BibTeX
@inproceedings{garg2008role,
author = {Neha P. Garg and Sarah Favre and Hugues Salamin and Dilek Hakkani-Tür and Alessandro Vinciarelli},
title = {{Role recognition for meeting participants: an approach based on lexical information and social network analysis}},
booktitle = {ACM Multimedia},
year = {2008},
url = {https://openreview.net/forum?id=ABz8dLe522O},
}Loading related content...