Incorporating Trustiness and Collective Synonym/ Contrastive Evidence into Taxonomy Construction

Abstract

In many applications, taxonomy plays a crucial role by organizing domain knowledge into a hierarchy of is-are relations between terms. Previous works on taxonomic relation identification from text corpora lack in two aspects:firstly, they do not consider the trustworthiness of individual source texts, which is important for filtering out incorrect relations from unreliable sources. Secondly, they also do not consider collective evidence from synonyms and contrastive terms, where synonyms may provide additional support to taxonomic relations, while contrastive terms may contradict them. In this paper, we present a method of taxonomic relation identification that incorporates the trustworthiness of source texts, measured with techniques like PageRank and knowledge-based trust, as well as the collective evidence of synonyms and contrastive terms identified through linguistic pattern matching and machine learning. The experimental results show that the proposed features consistently improve performance, with up to a 4% to 10% increase in F-measure.

Luu Anh Tuan

Assistant Professor

My research interests lie in the intersection of Artificial Intelligence and Natural Language Processing.