Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation
This addresses the problem of linking entity mentions to knowledge bases for NLP applications, representing an incremental improvement with specific gains.
The paper tackles Named Entity Disambiguation by proposing a joint embedding method that maps words and entities into the same vector space, achieving state-of-the-art accuracies of 93.1% on CoNLL and 85.2% on TAC 2010 datasets.
Named Entity Disambiguation (NED) refers to the task of resolving multiple named entity mentions in a document to their correct references in a knowledge base (KB) (e.g., Wikipedia). In this paper, we propose a novel embedding method specifically designed for NED. The proposed method jointly maps words and entities into the same continuous vector space. We extend the skip-gram model by using two models. The KB graph model learns the relatedness of entities using the link structure of the KB, whereas the anchor context model aims to align vectors such that similar words and entities occur close to one another in the vector space by leveraging KB anchors and their context words. By combining contexts based on the proposed embedding with standard NED features, we achieved state-of-the-art accuracy of 93.1% on the standard CoNLL dataset and 85.2% on the TAC 2010 dataset.