Leveraging Term Banks for Answering Complex Questions: A Case for Sparse Vectors

TL;DR

This paper introduces an unsupervised method that uses term banks and specialized vector spaces to improve the accuracy of answering complex science questions, outperforming existing QA systems.

Contribution

The authors propose a novel unsupervised approach leveraging term banks and multiple vector spaces to enhance complex question answering without extensive knowledge resource creation.

Findings

Significantly outperforms state-of-the-art QA systems on complex science questions

Demonstrates the effectiveness of specialized vector spaces for domain terminology

Shows that leveraging term banks improves answer accuracy for complex queries

Abstract

While open-domain question answering (QA) systems have proven effective for answering simple questions, they struggle with more complex questions. Our goal is to answer more complex questions reliably, without incurring a significant cost in knowledge resource construction to support the QA. One readily available knowledge resource is a term bank, enumerating the key concepts in a domain. We have developed an unsupervised learning approach that leverages a term bank to guide a QA system, by representing the terminological knowledge with thousands of specialized vector spaces. In experiments with complex science questions, we show that this approach significantly outperforms several state-of-the-art QA systems, demonstrating that significant leverage can be gained from continuous vector representations of domain terminology.