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

A Factorization Machine Framework for Testing Bigram Embeddings in Knowledgebase Completion

Welbl, J; Bouchard, G; Riedel, S; (2016) A Factorization Machine Framework for Testing Bigram Embeddings in Knowledgebase Completion. In: Proceedings of the 5th Workshop on Automated Knowledge Base Construction. (pp. pp. 103-107). Association for Computational Linguistics (ACL): San Diego, CA, USA. Green open access

[thumbnail of Riedel_W16-1319.pdf]
Preview
Text
Riedel_W16-1319.pdf - Published Version

Download (160kB) | Preview

Abstract

Embedding-based Knowledge Base Completion models have so far mostly combined distributed representations of individual entities or relations to compute truth scores of missing links. Facts can however also be represented using pairwise embeddings, i.e. embeddings for pairs of entities and relations. In this paper we explore such bigram embeddings with a flexible Factorization Machine model and several ablations from it. We investigate the relevance of various bigram types on the fb15k237 dataset and find relative improvements compared to a compositional model.

Type: Proceedings paper
Title: A Factorization Machine Framework for Testing Bigram Embeddings in Knowledgebase Completion
Event: 5th Workshop on Automated Knowledge Base Construction
Open access status: An open access version is available from UCL Discovery
DOI: 10.18653/v1/W16-1319
Publisher version: https://doi.org/10.18653/v1/W16-1319
Language: English
Additional information: This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/
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/10104709
Downloads since deposit
41Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item