Logical Neural Networks for Knowledge Base Completion with Embeddings & Rules

Prithviraj Sen, Breno William Carvalho, Ibrahim Abdelaziz, Pavan Kapanipathi, Salim Roukos, Alexander Gray


Abstract
Knowledge base completion (KBC) has benefitted greatly by learning explainable rules in an human-interpretable dialect such as first-order logic. Rule-based KBC has so far, mainly focussed on learning one of two types of rules: conjunction-of-disjunctions and disjunction-of-conjunctions. We qualitatively show, via examples, that one of these has an advantage over the other when it comes to achieving high quality KBC. To the best of our knowledge, we are the first to propose learning both kinds of rules within a common framework. To this end, we propose to utilize logical neural networks (LNN), a powerful neuro-symbolic AI framework that can express both kinds of rules and learn these end-to-end using gradient-based optimization. Our in-depth experiments show that our LNN-based approach to learning rules for KBC leads to roughly 10% relative improvements, if not more, over SotA rule-based KBC methods. Moreover, by showing how to combine our proposed methods with knowledge graph embeddings we further achieve an additional 7.5% relative improvement.
Anthology ID:
2022.emnlp-main.255
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3863–3875
Language:
URL:
https://aclanthology.org/2022.emnlp-main.255
DOI:
Bibkey:
Cite (ACL):
Prithviraj Sen, Breno William Carvalho, Ibrahim Abdelaziz, Pavan Kapanipathi, Salim Roukos, and Alexander Gray. 2022. Logical Neural Networks for Knowledge Base Completion with Embeddings & Rules. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3863–3875, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Logical Neural Networks for Knowledge Base Completion with Embeddings & Rules (Sen et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.emnlp-main.255.pdf