Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction
This work addresses the problem of ambiguous semantic parsing for users in knowledge-base question answering by enabling interactive corrections, though it is incremental as it builds on existing KBQA models with a new interactive layer.
The paper tackles the challenge of ambiguity in semantic parsing by introducing an interactive framework that explains predicted logical forms step-by-step and allows user corrections via natural-language feedback, focusing on KBQA to increase transparency and trust, with experiments showing potential for greatly improved parse accuracy and effectiveness across state-of-the-art models.
Existing studies on semantic parsing focus primarily on mapping a natural-language utterance to a corresponding logical form in one turn. However, because natural language can contain a great deal of ambiguity and variability, this is a difficult challenge. In this work, we investigate an interactive semantic parsing framework that explains the predicted logical form step by step in natural language and enables the user to make corrections through natural-language feedback for individual steps. We focus on question answering over knowledge bases (KBQA) as an instantiation of our framework, aiming to increase the transparency of the parsing process and help the user appropriately trust the final answer. To do so, we construct INSPIRED, a crowdsourced dialogue dataset derived from the ComplexWebQuestions dataset. Our experiments show that the interactive framework with human feedback has the potential to greatly improve overall parse accuracy. Furthermore, we develop a pipeline for dialogue simulation to evaluate our framework w.r.t. a variety of state-of-the-art KBQA models without involving further crowdsourcing effort. The results demonstrate that our interactive semantic parsing framework promises to be effective across such models.