Learning Multi-Relational Semantics Using Neural-Embedding Models

TL;DR

This paper introduces a unified framework for multi-relational embedding models, investigates various relation operators and entity representations, and achieves state-of-the-art results on Freebase knowledge base completion.

Contribution

It provides a comprehensive analysis of multi-relational embedding models and proposes a simple model that outperforms previous methods.

Findings

Relation operators significantly affect model performance

Pre-trained entity vectors improve embedding quality

Proposed model achieves new state-of-the-art on Freebase

Abstract

In this paper we present a unified framework for modeling multi-relational representations, scoring, and learning, and conduct an empirical study of several recent multi-relational embedding models under the framework. We investigate the different choices of relation operators based on linear and bilinear transformations, and also the effects of entity representations by incorporating unsupervised vectors pre-trained on extra textual resources. Our results show several interesting findings, enabling the design of a simple embedding model that achieves the new state-of-the-art performance on a popular knowledge base completion task evaluated on Freebase.