Joint learning of ontology and semantic parser from text

TL;DR

This paper introduces a novel joint learning approach that induces ontologies and semantic parsers from text using a semi-automatic grammar induction, demonstrated on Wikipedia biographies.

Contribution

It presents a new method for simultaneously learning ontologies and semantic parsers from text through grammar induction and semantic tree parsing.

Findings

Effective ontology learning from text.

Successful semantic parser induction.

Validated on Wikipedia biographies.

Abstract

Semantic parsing methods are used for capturing and representing semantic meaning of text. Meaning representation capturing all the concepts in the text may not always be available or may not be sufficiently complete. Ontologies provide a structured and reasoning-capable way to model the content of a collection of texts. In this work, we present a novel approach to joint learning of ontology and semantic parser from text. The method is based on semi-automatic induction of a context-free grammar from semantically annotated text. The grammar parses the text into semantic trees. Both, the grammar and the semantic trees are used to learn the ontology on several levels -- classes, instances, taxonomic and non-taxonomic relations. The approach was evaluated on the first sentences of Wikipedia pages describing people.