Representation Learning of Entities and Documents from Knowledge Base Descriptions

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.

PDF Abstract COLING 2018 PDF COLING 2018 Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text Classification 20NEWS TextEnt-full Accuracy 84.5 # 11
F-measure 83.9 # 4
Entity Typing Freebase FIGER TextEnt-full Accuracy 37.4 # 1
BEP 94.8 # 1
Macro F1 84.2 # 1
Micro F1 85.7 # 1
P@1 93.2 # 1
Text Classification R8 TextEnt-full Accuracy 96.7 # 10
F-measure 91 # 2

Methods


No methods listed for this paper. Add relevant methods here