Combining Search with Structured Data to Create a More Engaging User Experience in Open Domain Dialogue
This work addresses the problem of creating more engaging user experiences in open-domain dialogue systems, though it appears incremental as it builds on existing methods for integrating data sources.
The paper tackled the challenge of building open-domain conversational agents that can maintain coherent multi-turn dialogues by combining search results with structured data, resulting in an average conversation length of 8 minutes and 17 seconds during user evaluations.
The greatest challenges in building sophisticated open-domain conversational agents arise directly from the potential for ongoing mixed-initiative multi-turn dialogues, which do not follow a particular plan or pursue a particular fixed information need. In order to make coherent conversational contributions in this context, a conversational agent must be able to track the types and attributes of the entities under discussion in the conversation and know how they are related. In some cases, the agent can rely on structured information sources to help identify the relevant semantic relations and produce a turn, but in other cases, the only content available comes from search, and it may be unclear which semantic relations hold between the search results and the discourse context. A further constraint is that the system must produce its contribution to the ongoing conversation in real-time. This paper describes our experience building SlugBot for the 2017 Alexa Prize, and discusses how we leveraged search and structured data from different sources to help SlugBot produce dialogic turns and carry on conversations whose length over the semi-finals user evaluation period averaged 8:17 minutes.