# Learning Distributed Representations of Texts and Entities from Knowledge Base

arXiv: https://arxiv.org/abs/1705.02494 · HTML: https://mlsanity.com/paper/1705.02494/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2017.

## Built on by (most cited first, 10 of 10)

- [EASE: Entity-Aware Contrastive Learning of Sentence Embedding](https://mlsanity.com/paper/2205.04260/) (2022)
- [DOCENT: Learning Self-Supervised Entity Representations from Large Document Collections](https://mlsanity.com/paper/2102.13247/) (2021)
- [MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations](https://mlsanity.com/paper/2109.05716/) (2021)
- [Low-Rank Subspaces for Unsupervised Entity Linking](https://mlsanity.com/paper/2104.08737/) (2021)
- [Enriched Attention for Robust Relation Extraction](https://mlsanity.com/paper/2104.10899/) (2021)
- [Integrating a Heterogeneous Graph with Entity-aware Self-attention using Relative Position Labels for Reading Comprehension Model](https://mlsanity.com/paper/2307.10443/) (2023)
- [The X Types -- Mapping the Semantics of the Twitter Sphere](https://mlsanity.com/paper/2409.14584/) (2024)
- [TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation](https://mlsanity.com/paper/2504.18269/) (2025)
- [Efficient Entity Candidate Generation for Low-Resource Languages](https://mlsanity.com/paper/2206.15163/) (2022)
- [OASYS: Domain-Agnostic Automated System for Constructing Knowledge Base from Unstructured Text](https://mlsanity.com/paper/2207.07597/) (2022)

## Abstract (arXiv)

We describe a neural network model that jointly learns distributed representations of texts and knowledge base (KB) entities. Given a text in the KB, we train our proposed model to predict entities that are relevant to the text. Our model is designed to be generic with the ability to address various NLP tasks with ease. We train the model using a large corpus of texts and their entity annotations extracted from Wikipedia. We evaluated the model on three important NLP tasks (i.e., sentence textual similarity, entity linking, and factoid question answering) involving both unsupervised and supervised settings. As a result, we achieved state-of-the-art results on all three of these tasks. Our code and trained models are publicly available for further academic research.