Using semantically connected parse trees to answer multi-sentence queries
Dmitry Ilvovsky · Automatic Documentation and Mathematical Linguistics · 2014
This paper considers the problem of finding relevant answers to multi-sentence questions, which is urgent for many applied fields. In particular, this problem arises in industrial systems that are aimed at providing goods and services. One of the major approaches to this problem is that a set of potential answers that were obtained using a keyword search is repeatedly ordered by comparing syntactic answer parse trees with a question parse tree. This work modifies the approach based on using parse trees and improves it by passing to a more exact representation of semantic and syntactic text structure: the consideration of text paragraphs as a unit of analyzed information. The software implementation of the approach was performed and the results of the implementation were placed in open access as an adjustment for the Apache SOLR search engine, by which the suggested technology can be easily integrated with industrial search systems.