Knowledge-based Conversational Search

TL;DR

This thesis develops foundational methods for conversational search systems, analyzing dialogue structures, proposing a knowledge graph-based question answering approach, and exploring conversational browsing to improve information access.

Contribution

It introduces a comprehensive analysis of dialogue patterns, a novel knowledge graph question answering method, and a proactive conversational browsing approach for enhanced information retrieval.

Findings

Question answering is essential but not sufficient for effective conversational search.

Proposed knowledge graph approach outperforms existing methods in efficacy and efficiency.

Conversational browsing helps users discover relevant items beyond question answering capabilities.

Abstract

Conversational interfaces that allow for intuitive and comprehensive access to digitally stored information remain an ambitious goal. In this thesis, we lay foundations for designing conversational search systems by analyzing the requirements and proposing concrete solutions for automating some of the basic components and tasks that such systems should support. We describe several interdependent studies that were conducted to analyse the design requirements for more advanced conversational search systems able to support complex human-like dialogue interactions and provide access to vast knowledge repositories. In the first two research chapters, we focus on analyzing the structures common to information-seeking dialogues by capturing recurrent patterns in terms of both domain-independent functional relations between utterances as well as domain-specific implicit semantic relations from shared background knowledge. Our results show that question answering is one of the key components required for efficient information access but it is not the only type of dialogue interactions that a conversational search system should support. In the third research chapter, we propose a novel approach for complex question answering from a knowledge graph that surpasses the current state-of-the-art results in terms of both efficacy and efficiency. In the last research chapter, we turn our attention towards an alternative interaction mode, which we termed conversational browsing, in which, unlike question answering, the conversational system plays a more pro-active role in the course of a dialogue interaction. We show that this approach helps users to discover relevant items that are difficult to retrieve using only question answering due to the vocabulary mismatch problem.