Tell Me Why: Computational Explanation of Conceptual Similarity Judgments

Abstract

In this paper we introduce a system for the computation of explanations that accompany scores in the conceptual similarity task. In this setting the problem is, given a pair of concepts, to provide a score that expresses in how far the two concepts are similar. In order to explain how explanations are automatically built, we illustrate some basic features of COVER, the lexical resource that underlies our approach, and the main traits of the MeRaLi system, that computes conceptual similarity and explanations, all in one. To assess the computed explanations, we have designed a human experimentation, that provided interesting and encouraging results, which we report and discuss in depth.

Lexical Opposition in Discourse Contrast

“…As regards as future work, the simple averaging scheme on dependents' abstractness scores can be refined in many ways, e.g., by differentiating the contribution of different sorts of dependents, or based on their distribution. Yet, the set of relations that constitute the backbone of ABS-COVER can be further exploited both for computing the abstractness of dependents, and, in the long term, for generating explanations about the obtained abstractness scores, in virtue of the set of relations at the base of the explanatory power of COVER (Colla et al, 2018). Finally, we plan to explore whether and to what extent our lexical resource can be combined with distributional models, in order to pair those strong associative features with the more semantically structured space described by ABS-COVER.…”

Semantically Aware Text Categorisation for Metadata Annotation

“…The set of PHILO-ENTITIES can be used to build simple yet informative explanations of why a given record has been categorised as a philosophical one. This approach, based on simple templates such as the system described in [6] will be extended to build explanations also for non-philosophical records in next future. Let us consider, as an example, a record whose title is "Dialectic in the philosophy of Ernst Bloch"; this record has been marked as philosophical by human annotators.…”

COVER: a linguistic resource combining common sense and lexicographic information

“…8 Some examples of the explanations that can be generated based on the COVER resource; the terms at stake are marked with italic and bold font, while the dimensions are marked with italic font. The similarity values are on a scale from 0.00 to 4.00. yet achieve state-of-the-art scores (as reported in the next Section), the COVER resource allows to naturally build explanations for the computed similarity by simply enumerating the concepts shared along the dimensions of the vector representation [15], as illustrated in Figure 8. The ability to provide explanations justifying the obtained results is a feature shared by all mentioned applications built on top of COVER; at the best of our knowledge, none of the existing approaches allows to compute such explanation.…”