Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering

TL;DR

This paper introduces the IQN-KGQA test collection to evaluate and improve the naturalness of questions in knowledge graph question answering, revealing that more realistic questions can challenge existing systems.

Contribution

The study develops a new dataset with rewritten, more natural questions and analyzes their impact on KGQA system performance, highlighting challenges in dataset construction.

Findings

Some KGQA systems perform worse with more natural questions

The IQN-KGQA dataset enables realistic evaluation of KGQA models

Rewritten questions improve fluency but may affect system accuracy

Abstract

Knowledge graph question answering (KGQA) facilitates information access by leveraging structured data without requiring formal query language expertise from the user. Instead, users can express their information needs by simply asking their questions in natural language (NL). Datasets used to train KGQA models that would provide such a service are expensive to construct, both in terms of expert and crowdsourced labor. Typically, crowdsourced labor is used to improve template-based pseudo-natural questions generated from formal queries. However, the resulting datasets often fall short of representing genuinely natural and fluent language. In the present work, we investigate ways to characterize and remedy these shortcomings. We create the IQN-KGQA test collection by sampling questions from existing KGQA datasets and evaluating them with regards to five different aspects of naturalness. Then, the questions are rewritten to improve their fluency. Finally, the performance of existing KGQA models is compared on the original and rewritten versions of the NL questions. We find that some KGQA systems fare worse when presented with more realistic formulations of NL questions. The IQN-KGQA test collection is a resource to help evaluate KGQA systems in a more realistic setting. The construction of this test collection also sheds light on the challenges of constructing large-scale KGQA datasets with genuinely NL questions.