Modeling Paths for Explainable Knowledge Base Completion

Josua Stadelmaier, Sebastian Padó


Abstract
A common approach in knowledge base completion (KBC) is to learn representations for entities and relations in order to infer missing facts by generalizing existing ones. A shortcoming of standard models is that they do not explain their predictions to make them verifiable easily to human inspection. In this paper, we propose the Context Path Model (CPM) which generates explanations for new facts in KBC by providing sets of context paths as supporting evidence for these triples. For example, a new triple (Theresa May, nationality, Britain) may be explained by the path (Theresa May, born in, Eastbourne, contained in, Britain). The CPM is formulated as a wrapper that can be applied on top of various existing KBC models. We evaluate it for the well-established TransE model. We observe that its performance remains very close despite the added complexity, and that most of the paths proposed as explanations provide meaningful evidence to assess the correctness.
Anthology ID:
W19-4816
Volume:
Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Tal Linzen, Grzegorz Chrupała, Yonatan Belinkov, Dieuwke Hupkes
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
147–157
Language:
URL:
https://aclanthology.org/W19-4816
DOI:
10.18653/v1/W19-4816
Bibkey:
Cite (ACL):
Josua Stadelmaier and Sebastian Padó. 2019. Modeling Paths for Explainable Knowledge Base Completion. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 147–157, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Modeling Paths for Explainable Knowledge Base Completion (Stadelmaier & Padó, BlackboxNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4816.pdf
Code
 JosuaStadelmaier/CPM