Supporting search engines with knowledge and context

TL;DR

This thesis explores methods to enhance search engines by integrating knowledge and context, including knowledge retrieval, generation, and contextualization, as well as conversational search and support for professional news writers.

Contribution

It introduces new techniques for knowledge retrieval, automatic description generation, contextualization, and models for conversational search and news narrative support.

Findings

Effective retrieval of knowledge facts from text corpus

Improved query resolution in conversational search

Insights into ranking methods for news event narratives

Abstract

Search engines leverage knowledge to improve information access. In order to effectively leverage knowledge, search engines should account for context, i.e., information about the user and query. In this thesis, we aim to support search engines in leveraging knowledge while accounting for context. In the first part of this thesis, we study how to make structured knowledge more accessible to the user when the search engine proactively provides such knowledge as context to enrich search results. As a first task, we study how to retrieve descriptions of knowledge facts from a text corpus. Next, we study how to automatically generate knowledge fact descriptions. And finally, we study how to contextualize knowledge facts, that is, to automatically find facts related to a query fact. In the second part of this thesis, we study how to improve interactive knowledge gathering. We focus on conversational search, where the user interacts with the search engine to gather knowledge over large unstructured knowledge repositories. We focus on multi-turn passage retrieval as an instance of conversational search. We propose to model query resolution as a term classification task and propose a method to address it. In the final part of this thesis, we focus on search engine support for professional writers in the news domain. We study how to support such writers create event-narratives by exploring knowledge from a corpus of news articles. We propose a dataset construction procedure for this task that relies on existing news articles to simulate incomplete narratives and relevant articles. We study the performance of multiple rankers, lexical and semantic, and provide insights into the characteristics of this task.