English

Overview of the Ugglan Entity Discovery and Linking System

Computation and Language 2019-03-14 v1

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.

Keywords

Cite

@article{arxiv.1903.05498,
  title  = {Overview of the Ugglan Entity Discovery and Linking System},
  author = {Marcus Klang and Firas Dib and Pierre Nugues},
  journal= {arXiv preprint arXiv:1903.05498},
  year   = {2019}
}