Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering
This addresses the challenge of dataset quality for KGQA, which impacts users relying on natural language interfaces, though it is incremental as it focuses on improving existing data rather than a new method.
The paper tackles the problem of unnatural questions in knowledge graph question answering (KGQA) datasets by creating the IQN-KGQA test collection, which evaluates and rewrites questions for naturalness, and finds that some KGQA systems perform worse with more realistic questions.
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.