Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation

TL;DR

This paper introduces Entity-ELMo, a novel entity-aware extension of ELMo, which learns contextual entity representations to improve local entity disambiguation accuracy on benchmark datasets.

Contribution

The paper proposes Entity-ELMo, a new method for learning contextual entity representations that enhances local entity disambiguation performance.

Findings

Outperforms state-of-the-art models by 0.5% accuracy on AIDA test-b.

Utilizes a novel entity-aware extension of ELMo for better entity representation.

Achieves improved disambiguation results while maintaining fair training and candidate set conditions.

Abstract

We present a new local entity disambiguation system. The key to our system is a novel approach for learning entity representations. In our approach we learn an entity aware extension of Embedding for Language Model (ELMo) which we call Entity-ELMo (E-ELMo). Given a paragraph containing one or more named entity mentions, each mention is first defined as a function of the entire paragraph (including other mentions), then they predict the referent entities. Utilizing E-ELMo for local entity disambiguation, we outperform all of the state-of-the-art local and global models on the popular benchmarks by improving about 0.5\% on micro average accuracy for AIDA test-b with Yago candidate set. The evaluation setup of the training data and candidate set are the same as our baselines for fair comparison.