Abductive Matching in Question Answering
This work addresses the problem of improving accuracy and transparency in question-answering systems for users dealing with semi-structured data, though it is incremental as it builds on existing semantic parsing techniques.
The paper tackles question-answering over semi-structured data by introducing a method that combines machine learning for missing annotations with manually authored rules for parsing, achieving state-of-the-art performance of 40.42% accuracy on a standard benchmark dataset.
We study question-answering over semi-structured data. We introduce a new way to apply the technique of semantic parsing by applying machine learning only to provide annotations that the system infers to be missing; all the other parsing logic is in the form of manually authored rules. In effect, the machine learning is used to provide non-syntactic matches, a step that is ill-suited to manual rules. The advantage of this approach is in its debuggability and in its transparency to the end-user. We demonstrate the effectiveness of the approach by achieving state-of-the-art performance of 40.42% accuracy on a standard benchmark dataset over tables from Wikipedia.