TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Entity Linking	AIDA-CoNLL	Kannan Ravi et al. (2021)	Micro-F1 strong	83.1	# 8
Entity Linking	MSNBC	Kannan Ravi et al. (2021)	Micro-F1	83.4	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/cholan-a-modular-approach-for-neural-entity/entity-linking-on-msnbc-1)](https://paperswithcode.com/sota/entity-linking-on-msnbc-1?p=cholan-a-modular-approach-for-neural-entity)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/cholan-a-modular-approach-for-neural-entity/entity-linking-on-aida-conll)](https://paperswithcode.com/sota/entity-linking-on-aida-conll?p=cholan-a-modular-approach-for-neural-entity)`

CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata

EACL 2021 · Manoj Prabhakar Kannan Ravi, Kuldeep Singh, Isaiah Onando Mulang', Saeedeh Shekarpour, Johannes Hoffart, Jens Lehmann ·

In this paper, we propose CHOLAN, a modular approach to target end-to-end entity linking (EL) over knowledge bases. CHOLAN consists of a pipeline of two transformer-based models integrated sequentially to accomplish the EL task. The first transformer model identifies surface forms (entity mentions) in a given text. For each mention, a second transformer model is employed to classify the target entity among a predefined candidates list. The latter transformer is fed by an enriched context captured from the sentence (i.e. local context), and entity description gained from Wikipedia. Such external contexts have not been used in the state of the art EL approaches. Our empirical study was conducted on two well-known knowledge bases (i.e., Wikidata and Wikipedia). The empirical results suggest that CHOLAN outperforms state-of-the-art approaches on standard datasets such as CoNLL-AIDA, MSNBC, AQUAINT, ACE2004, and T-REx.