A Factorization Machine Framework for Testing Bigram Embeddings in Knowledgebase Completion
Computation and Language
2016-04-21 v1 Artificial Intelligence
Neural and Evolutionary Computing
Machine Learning
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.
Cite
@article{arxiv.1604.05878,
title = {A Factorization Machine Framework for Testing Bigram Embeddings in Knowledgebase Completion},
author = {Johannes Welbl and Guillaume Bouchard and Sebastian Riedel},
journal= {arXiv preprint arXiv:1604.05878},
year = {2016}
}
Comments
accepted for AKBC 2016 workshop, 6pages