Automatic Taxonomy Induction based on Word-embedding of Neural Nets

Abstract

Taxonomy is a knowledge management tool that presents useful information in a well-ordered structure prevents overloading of information on its access and making the information access qualitative. This article is concerned with automatically extracting asymmetrical hierarchical relations from a large corpus and subsequent taxonomy construction by domain independent and semi-supervised system. The methodology relies on the term’s distributional semantics. The algorithm utilizes the word-embedding generated from the vector space model. The model is trained over a large corpus to generate word-embedding of each word in a corpus. Then, the system finds and extracts the hypernyms by using the genetic algorithm based on distributional semantics calculations. In the last step, the system adds hyponym-hypernym relations extracted from the string comparison module. Gold Standards taxonomies are used to evaluate the system’s taxonomies for each domain. Our system achieved significant results across each domain.