Name
Title | ||
|---|---|---|
Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation |
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-the-art accuracy of 93.1% on the standard CoNLL dataset and 85.2% on the TAC 2010 dataset. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.18653/v1/K16-1025 | CoNLL |
Field | DocType | Volume |
Entity linking,Vector space,Embedding,Computer science,Context model,Named entity,Natural language processing,Artificial intelligence,Knowledge base,Graph model | Journal | abs/1601.01343 |
Citations | PageRank | References |
35 | 0.87 | 21 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ikuya Yamada | 1 | 65 | 8.25 |
| Hiroyuki Shindo | 2 | 75 | 13.80 |
| Hideaki Takeda | 3 | 179 | 25.16 |
| Yoshiyasu Takefuji | 4 | 262 | 33.68 |