Representation Learning of Entities and Documents from Knowledge Base Descriptions
arXiv:1806.02960
Abstract
In this paper, we describe TextEnt, a neural network model that learns distributed representations of entities and documents directly from a knowledge base (KB). Given a document in a KB consisting of words and entity annotations, we train our model to predict the entity that the document describes and map the document and its target entity close to each other in a continuous vector space. Our model is trained using a large number of documents extracted from Wikipedia. The performance of the proposed model is evaluated using two tasks, namely fine-grained entity typing and multiclass text classification. The results demonstrate that our model achieves state-of-the-art performance on both tasks. The code and the trained representations are made available online for further academic research.
arXiv commentAccepted at COLING 2018
References in corpus (5)
- Adam: A Method for Stochastic Optimization
- Efficient Estimation of Word Representations in Vector Space
- ADADELTA: An Adaptive Learning Rate Method
- Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation
- Inferring Missing Entity Type Instances for Knowledge Base Completion: New Dataset and Methods