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

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.

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• Neural Cross-Lingual Entity Linking
• Joint Neural Entity Disambiguation with Output Space Search

Cited by in corpus (5)

• Autoregressive Entity Retrieval
• Neural Entity Linking: A Survey of Models Based on Deep Learning
• Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation
• Entity Linking Meets Deep Learning: Techniques and Solutions
• Read, Retrospect, Select: An MRC Framework to Short Text Entity Linking