IntKB: A Verifiable Interactive Framework for Knowledge Base Completion

Bernhard Kratzwald, Guo Kunpeng, Stefan Feuerriegel, Dennis Diefenbach


Abstract
Knowledge bases (KBs) are essential for many downstream NLP tasks, yet their prime shortcoming is that they are often incomplete. State-of-the-art frameworks for KB completion often lack sufficient accuracy to work fully automated without human supervision. As a remedy, we propose : a novel interactive framework for KB completion from text based on a question answering pipeline. Our framework is tailored to the specific needs of a human-in-the-loop paradigm: (i) We generate facts that are aligned with text snippets and are thus immediately verifiable by humans. (ii) Our system is designed such that it continuously learns during the KB completion task and, therefore, significantly improves its performance upon initial zero- and few-shot relations over time. (iii) We only trigger human interactions when there is enough information for a correct prediction. Therefore, we train our system with negative examples and a fold-option if there is no answer. Our framework yields a favorable performance: it achieves a hit@1 ratio of 29.7% for initially unseen relations, upon which it gradually improves to 46.2%.
Anthology ID:
2020.coling-main.490
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5591–5603
Language:
URL:
https://aclanthology.org/2020.coling-main.490
DOI:
10.18653/v1/2020.coling-main.490
Bibkey:
Cite (ACL):
Bernhard Kratzwald, Guo Kunpeng, Stefan Feuerriegel, and Dennis Diefenbach. 2020. IntKB: A Verifiable Interactive Framework for Knowledge Base Completion. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5591–5603, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
IntKB: A Verifiable Interactive Framework for Knowledge Base Completion (Kratzwald et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.490.pdf
Code
 bernhard2202/intkb
Data
NELL