Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation
This work addresses entity disambiguation for natural language processing applications, representing an incremental advance over existing methods.
The paper tackles entity disambiguation by proposing Entity-ELMo, a novel approach for learning contextual entity representations, and achieves state-of-the-art results with a 0.5% improvement in micro average accuracy on the AIDA test-b benchmark.
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.