Neural Attentive Bag-of-Entities Model for Text Classification

CONLL 2019  ·  Ikuya Yamada, Hiroyuki Shindo ·

This study proposes a Neural Attentive Bag-of-Entities model, which is a neural network model that performs text classification using entities in a knowledge base. Entities provide unambiguous and relevant semantic signals that are beneficial for capturing semantics in texts. We combine simple high-recall entity detection based on a dictionary, to detect entities in a document, with a novel neural attention mechanism that enables the model to focus on a small number of unambiguous and relevant entities. We tested the effectiveness of our model using two standard text classification datasets (i.e., the 20 Newsgroups and R8 datasets) and a popular factoid question answering dataset based on a trivia quiz game. As a result, our model achieved state-of-the-art results on all datasets. The source code of the proposed model is available online at

PDF Abstract CONLL 2019 PDF CONLL 2019 Abstract


  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 NABoE-full Accuracy 88.1 # 4
F-measure 86.2 # 2
Text Classification R8 NABoE-full Accuracy 97.9 # 2
F-measure 91.7 # 1


No methods listed for this paper. Add relevant methods here