Semantic Similarity Measures Applied to an Ontology for Human-Like Interaction

Abstract

The focus of this paper is the calculation of similarity between two concepts from an ontology for a Human-Like Interaction system. In order to facilitate this calculation, a similarity function is proposed based on five dimensions (sort, compositional, essential, restrictive and descriptive) constituting the structure of ontological knowledge. The paper includes a proposal for computing a similarity function for each dimension of knowledge. Later on, the similarity values obtained are weighted and aggregated to obtain a global similarity measure. In order to calculate those weights associated to each dimension, four training methods have been proposed. The training methods differ in the element to fit: the user, concepts or pairs of concepts, and a hybrid approach. For evaluating the proposal, the knowledge base was fed from WordNet and extended by using a knowledge editing toolkit (Cognos). The evaluation of the proposal is carried out through the comparison of system responses with those given by human test subjects, both providing a measure of the soundness of the procedure and revealing ways in which the proposal may be improved.

Dimensions of Ontological Similarity

“…It should be stressed that the proposed approach is flexible as: (i) it still allows attempts at domain/ontology specific methods to combine separate scores into a single one (as in, [1], [2]), (ii) it is possible to restrict similarity dimensions that are actually considered in a given domain (e.g. only taxonomic and compositional dimensions), based on the "nature of the application.…”

“…Note that this is not a judgment about correctness or usefulness of such methods. As a matter of fact, these application specific methods may work best in capturing the "nature of the specific problem" (similarly to training weights in [1]). …”

“…They can utilize dictionaries and lexical ontologies (such as WordNet) to asses similarity of entities (see [1]). A simple lexical method could, for instance, extract concept labels and use WordNet's synsets of these labels as features, in a feature-based method.…”

“…In [1] authors used a weighted sum of 5 dimensional similarity scores, and weights trained against human-based similarity scores. The suggested advantage of this approach is that the final score combines "all available knowledge."…”

A Conceptual Graph-Based Method to Compute Information Content

“…There are ontology-based approaches oriented towards computing similarity between a pair of concepts in an ontological structure. For instance, Albacete et al ( 2012) [79] defined a similarity function that requires information on five features: compositional, gender, fundamental, limitate, and illustrative. The weighted and combined similitude values generated a general similarity method, tested using the WordNet ontology.…”