Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models
Full Text: 16229-77263-1-PB.pdfIn this paper, we address the problem of speaker classification in multi-party conversation, and collect massive data to facilitate research in this direction. We further investigate temporal-based and content-based models of speakers, and propose several hybrids of them. Experiments show that speaker classification is feasible, and that hybrid models outperform each single component.
Citation
Z. Meng, L. Mou, Z. Jin. "Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models". National Conference on Artificial Intelligence (AAAI), pp 8121-8122, February 2018.Keywords: | Dialog systems, Speaker modeling |
Category: | In Conference |
Web Links: | AAAI |
BibTeX
@incollection{Meng+al:AAAI18, author = {Zhao Meng and Lili Mou and Zhi Jin}, title = {Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models}, Pages = {8121-8122}, booktitle = {National Conference on Artificial Intelligence (AAAI)}, year = 2018, }Last Updated: February 03, 2021
Submitted by Sabina P