Abductive Matching in Question Answering

2017/09/10 by Kedar Dhamdhere, Dhamdhere, Kedar, Kevin S. McCurley +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #H.3.3 #I.2.1 #Machine Learning (cs.LG) #cs.CL #cs.LG

paper · pdf · doi:10.48550/arxiv.1709.03036

arxiv created 2017/09/10 · arxiv updated 2017/09/12

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.

Related

• TAPAS: Weakly Supervised Table Parsing via Pre-training
• Knowledge Base Question Answering: A Semantic Parsing Perspective
• Question Answering over Unstructured Data without Domain Restrictions
• An Unsupervised Model with Attention Autoencoders for Question Retrieval
• Evaluating Semantic Parsing against a Simple Web-based Question Answering Model