UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Lifted Rule Injection for Relation Embeddings

Demeester, T; Rocktäschel, T; Riedel, S; (2016) Lifted Rule Injection for Relation Embeddings. In: Su, J and Duh, K and Carreras, X, (eds.) Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. (pp. pp. 1389-1399). Association for Computational Linguistics/Curran Associates Green open access

[thumbnail of 1606.08359v2.pdf]
Preview
Text
1606.08359v2.pdf - Published Version

Download (574kB) | Preview

Abstract

Methods based on representation learning currently hold the state-of-the-art in many natural language processing and knowledge base inference tasks. Yet, a major challenge is how to efficiently incorporate commonsense knowledge into such models. A recent approach regularizes relation and entity representations by propositionalization of first-order logic rules. However, propositionalization does not scale beyond domains with only few entities and rules. In this paper we present a highly efficient method for incorporating implication rules into distributed representations for automated knowledge base construction. We map entity-tuple embeddings into an approximately Boolean space and encourage a partial ordering over relation embeddings based on implication rules mined from WordNet. Surprisingly, we find that the strong restriction of the entity-tuple embedding space does not hurt the expressiveness of the model and even acts as a regularizer that improves generalization. By incorporating few commonsense rules, we achieve an increase of 2 percentage points mean average precision over a matrix factorization baseline, while observing a negligible increase in runtime.

Type: Proceedings paper
Title: Lifted Rule Injection for Relation Embeddings
Event: EMNLP 2016, Conference on Empirical Methods in Natural Language Processing, 1-5 November 2016, Austin, Texas
ISBN-13: 9781945626258
Open access status: An open access version is available from UCL Discovery
DOI: 10.18653/v1/D16-1146
Publisher version: https://aclanthology.coli.uni-saarland.de/papers/D...
Language: English
Additional information: This is the published version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/1527366
Downloads since deposit
86Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item