Interactively Diagnosing Errors in a Semantic Parser
This work addresses the burden of maintaining inspectable natural language systems for developers, but it is incremental as it focuses on early stages and synthetic data.
The paper tackles the problem of reducing maintenance effort for hand-curated natural language systems by proposing an interactive error diagnosis system for the CNLU semantic parser, casting debugging as a reasoning problem to diagnose semantic errors on synthetic examples.
Hand-curated natural language systems provide an inspectable, correctable alternative to language systems based on machine learning, but maintaining them requires considerable effort and expertise. Interactive Natural Language Debugging (INLD) aims to lessen this burden by casting debugging as a reasoning problem, asking the user a series of questions to diagnose and correct errors in the system's knowledge. In this paper, we present work in progress on an interactive error diagnosis system for the CNLU semantic parser. We show how the first two stages of the INLD pipeline (symptom identification and error localization) can be cast as a model-based diagnosis problem, demonstrate our system's ability to diagnose semantic errors on synthetic examples, and discuss design challenges and frontiers for future work.