Question Answering Against Very-Large Text Collections

TL;DR

This paper discusses enhancing a question answering system called Answer Finder, which aims to directly provide concise answers from large text collections by improving retrieval and pre-processing techniques.

Contribution

The paper introduces improvements to Answer Finder's information retrieval and question analysis pre-processing methods.

Findings

Enhanced retrieval accuracy in Answer Finder

More efficient question pre-processing techniques

Improved answer precision from large text collections

Abstract

Question answering involves developing methods to extract useful information from large collections of documents. This is done with specialised search engines such as Answer Finder. The aim of Answer Finder is to provide an answer to a question rather than a page listing related documents that may contain the correct answer. So, a question such as "How tall is the Eiffel Tower" would simply return "325m" or "1,063ft". Our task was to build on the current version of Answer Finder by improving information retrieval, and also improving the pre-processing involved in question series analysis.