English

Abductive Matching in Question Answering

Computation and Language 2017-09-12 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1709.03036,
  title  = {Abductive Matching in Question Answering},
  author = {Kedar Dhamdhere and Kevin S. McCurley and Mukund Sundararajan and Ankur Taly},
  journal= {arXiv preprint arXiv:1709.03036},
  year   = {2017}
}
R2 v1 2026-06-22T21:38:06.965Z