PolyResponse: A Rank-based Approach to Task-Oriented Dialogue with Application in Restaurant Search and Booking
This addresses the problem of building simpler, scalable task-oriented dialogue systems for users in domains like restaurant services, though it appears incremental as it builds on retrieval-based methods.
The authors tackled the complexity of traditional task-oriented dialogue systems by introducing PolyResponse, a retrieval-based conversational search engine that learns from real conversations to rank responses, resulting in a system available in 8 languages for restaurant search and booking.
We present PolyResponse, a conversational search engine that supports task-oriented dialogue. It is a retrieval-based approach that bypasses the complex multi-component design of traditional task-oriented dialogue systems and the use of explicit semantics in the form of task-specific ontologies. The PolyResponse engine is trained on hundreds of millions of examples extracted from real conversations: it learns what responses are appropriate in different conversational contexts. It then ranks a large index of text and visual responses according to their similarity to the given context, and narrows down the list of relevant entities during the multi-turn conversation. We introduce a restaurant search and booking system powered by the PolyResponse engine, currently available in 8 different languages.