Interpreting embedding models of knowledge bases.

• Ano de defesa: 2018
• Autor(a) principal: Gusmão, Arthur Colombini
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: eng
• Instituição de defesa: Biblioteca Digitais de Teses e Dissertações da USP
• Palavras-chave em Português: Aprendizado computacional; Conhecimento; Embedding models; Explainable AI; IA explicável; Interpretabilidade; Interpretability; Knowledge bases; Knowledge graphs; Modelos de incorporação; Relational machine learning
• Link de acesso: http://www.teses.usp.br/teses/disponiveis/3/3141/tde-04022019-094854/

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.