Investigations on Knowledge Base Embedding for Relation Prediction and Extraction

TL;DR

This paper evaluates knowledge base embedding models for relation prediction and extraction, introduces a larger benchmark, and finds that while effective for prediction, they do not improve neural relation extraction with current strategies.

Contribution

It provides a comprehensive evaluation of existing models and introduces a new, more complex benchmark for relation tasks.

Findings

Knowledge base embeddings are effective for relation prediction.

Current methods do not improve neural relation extraction.

Limitations of existing embedding strategies are identified.

Abstract

We report an evaluation of the effectiveness of the existing knowledge base embedding models for relation prediction and for relation extraction on a wide range of benchmarks. We also describe a new benchmark, which is much larger and complex than previous ones, which we introduce to help validate the effectiveness of both tasks. The results demonstrate that knowledge base embedding models are generally effective for relation prediction but unable to give improvements for the state-of-art neural relation extraction model with the existing strategies, while pointing limitations of existing methods.