Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation
Citations Over TimeTop 1% of 2016 papers
Abstract
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-theart accuracy of 93.1% on the standard CoNLL dataset and 85.2% on the TAC 2010 dataset.
Related Papers
- → Entity Linking: An Issue to Extract Corresponding Entity With Knowledge Base(2018)50 cited
- → Linking Entities in Short Texts Based on a Chinese Semantic Knowledge Base(2013)9 cited
- → Populating knowledge base with collective entity mentions: a graph-based approach(2014)2 cited
- → Entity Disambiguation for Knowledge Base Population(2010)343 cited
- → An Attention-Based Entity Linking Method for Chinese Knowledge Base Question Answering System(2023)