StalemateBreaker: A Proactive Content-Introducing Approach to Automatic Human-Computer Conversation
Full Text: 404.pdf
Existing open-domain human-computer conversation systems are typically passive: they either synthesize or retrieve a reply provided with a human-issued utterance. It is generally presumed that humans should take the role to lead the conversation and introduce new content when a stalemate occurs, and that computers only need to "respond." In this paper, we propose STALEMATEBREAKER, a conversation system that can proactively introduce new content when appropriate. We design a pipeline to determine when, what, and how to introduce new content during human-computer conversation. We further propose a novel reranking algorithm Bi-PageRank-HITS to enable rich interaction between conversation context and candidate replies. Experiments show that both the content-introducing approach and the reranking algorithm are effective. Our full STALEMATEBREAKER model outperforms a state-of-the-practice conversation system by +14.4% p@1 when a stalemate occurs.
Citation
X. Li, L. Mou, R. Yan, M. Zhang. "StalemateBreaker: A Proactive Content-Introducing Approach to Automatic Human-Computer Conversation". International Joint Conference on Artificial Intelligence (IJCAI), pp 2845-2851, February 2016.| Keywords: | |
| Category: | In Conference |
| Web Links: | IJCAI |
BibTeX
@incollection{Li+al:IJCAI16,
author = {Xiang Li and Lili Mou and Rui Yan and Ming Zhang},
title = {StalemateBreaker: A Proactive Content-Introducing Approach to
Automatic Human-Computer Conversation},
Pages = {2845-2851},
booktitle = {International Joint Conference on Artificial Intelligence
(IJCAI)},
year = 2016,
}Last Updated: February 04, 2021Submitted by Sabina P
