Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation
arXiv:1601.01343
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.
Accepted at CoNLL 2016
References in corpus (1)
Cited by in corpus (15)
- Autoregressive Entity Retrieval
- Neural Collective Entity Linking
- An Open-World Extension to Knowledge Graph Completion Models
- Joint Embedding of Hierarchical Categories and Entities for Concept Categorization and Dataless Classification
- Learning and Transferring IDs Representation in E-commerce
- Fast End-to-End Wikification
- End-to-End Neural Entity Linking
- Learning Distributed Representations of Texts and Entities from Knowledge Base
- Scalable graph-based individual named entity identification
- Collective Entity Disambiguation with Structured Gradient Tree Boosting
- Improving Neural Question Generation using World Knowledge
- Representation Learning of Entities and Documents from Knowledge Base Descriptions
- Joint Entity Linking with Deep Reinforcement Learning
- Learning Dynamic Context Augmentation for Global Entity Linking
- Microblog Topic Identification using Linked Open Data