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

arXiv: https://arxiv.org/abs/1909.01259 · HTML: https://mlsanity.com/paper/1909.01259/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution](https://mlsanity.com/paper/2107.02286/) (2021)
- [Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training](https://mlsanity.com/paper/2409.04707/) (2024)
- [GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction](https://mlsanity.com/paper/2503.11227/) (2025)
- [Automatic Detection of Entity-Manipulated Text using Factual Knowledge](https://mlsanity.com/paper/2203.10343/) (2022)
- [What You Say Is What You Show: Visual Narration Detection in Instructional Videos](https://mlsanity.com/paper/2301.02307/) (2023)
- [A Multilingual Bag-of-Entities Model for Zero-Shot Cross-Lingual Text Classification](https://mlsanity.com/paper/2110.07792/) (2021)
- [Global Hierarchical Neural Networks using Hierarchical Softmax](https://mlsanity.com/paper/2308.01210/) (2023)
- [An Explainable Probabilistic Classifier for Categorical Data Inspired to Quantum Physics](https://mlsanity.com/paper/2105.13988/) (2021)
- [Evaluation of Representation Models for Text Classification with AutoML Tools](https://mlsanity.com/paper/2106.12798/) (2021)

## Abstract (arXiv)

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.