IQA: Interactive Query Construction in Semantic Question Answering Systems

TL;DR

This paper introduces IQA, an interactive scheme for semantic question answering systems that incorporates user feedback through a novel metric, Option Gain, to improve query accuracy with minimal interaction.

Contribution

It proposes a new interaction scheme and a metric, Option Gain, to enhance user-guided query construction in semantic question answering systems.

Findings

Small user interactions significantly improve system performance.

Option Gain effectively guides user feedback for better query matching.

The scheme seamlessly integrates into existing SQA pipelines.

Abstract

Semantic Question Answering (SQA) systems automatically interpret user questions expressed in a natural language in terms of semantic queries. This process involves uncertainty, such that the resulting queries do not always accurately match the user intent, especially for more complex and less common questions. In this article, we aim to empower users in guiding SQA systems towards the intended semantic queries through interaction. We introduce IQA - an interaction scheme for SQA pipelines. This scheme facilitates seamless integration of user feedback in the question answering process and relies on Option Gain - a novel metric that enables efficient and intuitive user interaction. Our evaluation shows that using the proposed scheme, even a small number of user interactions can lead to significant improvements in the performance of SQA systems.