Natural language question answering and analytics for diverse and interlinked datasets

by Dezhao Song, Frank Schilder, Charese Smiley

Abstract:

Previous systems for natural language questions over complex linked datasets require the user to enter a complete and wellformed question, and present the answers as raw lists of entities. Using a featurebased grammar with a full formal semantics, we have developed a system that is able to support rich autosuggest, and to deliver dynamically generated analytics for each result that it returns.
 

Reference:

Dezhao Song, Frank Schilder, Charese Smiley, and Chris Brew, Natural language question answering and analytics for diverse and interlinked datasets, Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations (Denver, Colorado), Association for Computational Linguistics, June 2015, pp. 101–105.

Related articles

Our system, called TR Discover, maps from a fragment of English into an intermediate First Order Logic representation, which is in turn mapped into SPARQL or SQL. This makes crucial use of a feature-based grammar with full formal semantics.

A novel yet simple method is proposed to exercise in stock market by following successful stock market expert in social media.

This book constitutes the refereed postproceedings of two workshops held at the 5th International Conference on Social Informatics, SocInfo 2013, in Kyoto, Japan.