Authors: Hisao Katsumi,Takuya Hiraoka,Koichiro Yoshino,Kazeto Yamamoto,Shota Motoura,Kunihiko Sadamasa,Satoshi Nakamura
ArXiv: 1811.10728
Document:
PDF
DOI
Abstract URL: http://arxiv.org/abs/1811.10728v1
Argumentation-based dialogue systems, which can handle and exchange arguments
through dialogue, have been widely researched. It is required that these
systems have sufficient supporting information to argue their claims
rationally; however, the systems often do not have enough of such information
in realistic situations. One way to fill in the gap is acquiring such missing
information from dialogue partners (information-seeking dialogue). Existing
information-seeking dialogue systems are based on handcrafted dialogue
strategies that exhaustively examine missing information. However, the proposed
strategies are not specialized in collecting information for constructing
rational arguments. Moreover, the number of system's inquiry candidates grows
in accordance with the size of the argument set that the system deal with. In
this paper, we formalize the process of information-seeking dialogue as Markov
decision processes (MDPs) and apply deep reinforcement learning (DRL) for
automatically optimizing a dialogue strategy. By utilizing DRL, our dialogue
strategy can successfully minimize objective functions, the number of turns it
takes for our system to collect necessary information in a dialogue. We
conducted dialogue experiments using two datasets from different domains of
argumentative dialogue. Experimental results show that the proposed
formalization based on MDP works well, and the policy optimized by DRL
outperformed existing heuristic dialogue strategies.