Middle Expression and Its Converter from Natural Language for Conversation Game “Mafia”

Abstract

Recently, end-to-end learning is frequently used to implement dialogue systems. However, existing systems still suffer from issues to handle complex dialogues. In this paper, we target on the conversation game “Mafia”, which requires players to make consistent and complex communications. We propose a middle language expression and a converter from natural language input. We implemented our dialogue system to play the Mafia game with humans and other automatic agents. Our evaluation on the play shows that our middle language increases conversion coverage.