Exploiting Sublanguage and Domain Characteristics in a Bootstrapping Approach to Lexicon and Ontology Creation

TL;DR

This paper discusses ongoing experiments using bootstrapping techniques to automatically create lexicons and ontologies, addressing the high costs and coverage issues in building domain-specific lexical resources.

Contribution

It introduces a novel bootstrapping approach that exploits sublanguage and domain characteristics for efficient lexicon and ontology development.

Findings

Initial experiments show promising results in domain coverage improvement

Bootstrapping reduces manual effort in resource creation

Method adapts to different domain characteristics

Abstract

It is very costly to build up lexical resources and domain ontologies. Especially when confronted with a new application domain lexical gaps and a poor coverage of domain concepts are a problem for the successful exploitation of natural language document analysis systems that need and exploit such knowledge sources. In this paper we report about ongoing experiments with `bootstrapping techniques' for lexicon and ontology creation.