# Overview of the Ugglan Entity Discovery and Linking System

## TL;DR

Ugglan is a comprehensive entity discovery and linking system that combines dictionaries, NER, candidate generation, graph-based disambiguation, and reranking to improve entity linking accuracy.

## Contribution

The paper introduces an integrated system that combines multiple modules and data sources for improved entity discovery and linking performance.

## Key findings

- Uses Wikipedia and Wikidata dictionaries for entity recognition.
- Employs a graph-based disambiguation approach with PageRank.
- Achieves effective entity linking on TAC datasets.

## Abstract

Ugglan is a system designed to discover named entities and link them to unique identifiers in a knowledge base. It is based on a combination of a name and nominal dictionary derived from Wikipedia and Wikidata, a named entity recognition module (NER) using fixed ordinally-forgetting encoding (FOFE) trained on the TAC EDL data from 2014-2016, a candidate generation module from the Wikipedia link graph across multiple editions, a PageRank link and cooccurrence graph disambiguator, and finally a reranker trained on the TAC EDL 2015-2016 data.