Interpreting embedding models of knowledge bases.

Author(s)

Arthur Colombini Gusmão

• Document type: Master's Dissertation
• Press: São Paulo.
• Institution: Universidade de São Paulo (USP). Escola Politécnica (EP/BC)
• Defense date: 2018-11-26

Examining board members

Fabio Gagliardi Cozman; Etienne Américo Cartolano Junior; Bernardo Nunes Gonçalves

• Advisor: Fabio Gagliardi Cozman

Abstract

Knowledge bases are employed in a variety of applications, from natural language processing to semantic web search; alas, in practice, their usefulness is hurt by their incompleteness. To address this issue, several techniques aim at performing knowledge base completion, of which embedding models are efficient, attain state-of-the-art accuracy, and eliminate the need for feature engineering. However, embedding models predictions are notoriously hard to interpret. In this work, we propose model-agnostic methods that allow one to interpret embedding models by extracting weighted Horn rules from them. More specifically, we show how the so-called \"pedagogical techniques\", from the literature on neural networks, can be adapted to take into account the large-scale relational aspects of knowledge bases, and show experimentally their strengths and weaknesses. (AU)

• FAPESP's process: 17/19007-6 - Inference and learning algorithms for probabilistic logic programming
• Grantee: Arthur Colombini Gusmão
• Support Opportunities: Scholarships in Brazil - Master