TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Entity Disambiguation	AIDA-CoNLL	NTEE	In-KB Accuracy	94.7	# 4
Entity Disambiguation	TAC2010	NTEE	Micro Precision	87.7	# 2

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-distributed-representations-of-texts/entity-disambiguation-on-tac2010)](https://paperswithcode.com/sota/entity-disambiguation-on-tac2010?p=learning-distributed-representations-of-texts)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-distributed-representations-of-texts/entity-disambiguation-on-aida-conll)](https://paperswithcode.com/sota/entity-disambiguation-on-aida-conll?p=learning-distributed-representations-of-texts)`

Learning Distributed Representations of Texts and Entities from Knowledge Base

TACL 2017 · Ikuya Yamada, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji ·

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.