# Neural Attentive Bag-of-Entities Model for Text Classification

Source: [Neural Attentive Bag-of-Entities Model for Text Classification](<https://www.sota2.com/research/paper/68fa66541e209131cea0f831>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:09:15.223Z

Authors: Ikuya Yamada, Hiroyuki Shindo

Published: 2019-09-03T15:50:34.000Z

## Abstract

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 https://github.com/wikipedia2vec/wikipedia2vec.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Factoid Question Answering on History factoid QA (test)](<https://www.sota2.com/research/sota/factoid-question-answering-on-history-factoid-qa-test.md>): Factoid Question Answering; History factoid QA (test); Accuracy: 94.9.

- [Factoid Question Answering on Quiz Bowl Literature category](<https://www.sota2.com/research/sota/factoid-question-answering-on-quiz-bowl-literature-category.md>): Factoid Question Answering; Quiz Bowl Literature category; Accuracy: 98.5.

- [Text Classification on 20 Newsgroups by-date (test)](<https://www.sota2.com/research/sota/text-classification-on-20-newsgroups-by-date-test.md>): Text Classification; 20 Newsgroups by-date (test); Accuracy: 86.8.

- [Text classification on R8 (test)](<https://www.sota2.com/research/sota/text-classification-on-r8-test.md>): Text Classification; R8 (test); Accuracy: 97.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1909.01259>)

[PDF](<https://arxiv.org/pdf/1909.01259.pdf>)

[Implementation](<https://github.com/wikipedia2vec/wikipedia2vec>)