Question Answering over Unstructured Data without Domain Restrictions

TL;DR

This paper demonstrates that a practical and portable English question answering system over unstructured data can be quickly built using off-the-shelf tools, leveraging semantic parsing and WordNet for matching.

Contribution

It introduces a fast, adaptable NLQA system based on RMRS, showing how to implement and evaluate it with minimal setup and without domain restrictions.

Findings

System built with off-the-shelf parsers and thesauri

Uses RMRS for semantic representation

Achieves effective question answering over unstructured data

Abstract

Information needs are naturally represented as questions. Automatic Natural-Language Question Answering (NLQA) has only recently become a practical task on a larger scale and without domain constraints. This paper gives a brief introduction to the field, its history and the impact of systematic evaluation competitions. It is then demonstrated that an NLQA system for English can be built and evaluated in a very short time using off-the-shelf parsers and thesauri. The system is based on Robust Minimal Recursion Semantics (RMRS) and is portable with respect to the parser used as a frontend. It applies atomic term unification supported by question classification and WordNet lookup for semantic similarity matching of parsed question representation and free text.