RubyStar: A Non-Task-Oriented Mixture Model Dialog System
This work addresses the challenge of building more engaging and natural dialog systems for general conversation, though it appears incremental as it combines existing methods without a major breakthrough.
The authors tackled the problem of creating human-like conversation in non-task-oriented dialog systems by combining rule-based, retrieval-based, and generative methods, finding that character-level RNNs are effective for general responses with proper parameter settings.
RubyStar is a dialog system designed to create "human-like" conversation by combining different response generation strategies. RubyStar conducts a non-task-oriented conversation on general topics by using an ensemble of rule-based, retrieval-based and generative methods. Topic detection, engagement monitoring, and context tracking are used for managing interaction. Predictable elements of conversation, such as the bot's backstory and simple question answering are handled by separate modules. We describe a rating scheme we developed for evaluating response generation. We find that character-level RNN is an effective generation model for general responses, with proper parameter settings; however other kinds of conversation topics might benefit from using other models.