PolyResponse: A Rank-based Approach to Task-Oriented Dialogue with Application in Restaurant Search and Booking

TL;DR

PolyResponse is a retrieval-based conversational search engine for task-oriented dialogue, capable of handling multi-turn interactions in multiple languages without relying on explicit ontologies, demonstrated in restaurant search and booking.

Contribution

It introduces a novel rank-based approach that bypasses traditional complex dialogue system components and explicit semantics, trained on extensive real conversation data.

Findings

Supports multi-turn dialogue in 8 languages

Effectively ranks relevant responses based on conversational context

Enables restaurant search and booking without explicit ontologies

Abstract

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.