Overview of the Ugglan Entity Discovery and Linking System
This is an incremental system for entity linking, primarily relevant to researchers and practitioners in natural language processing and information extraction.
The paper tackles the problem of named entity discovery and linking by presenting the Ugglan system, which integrates multiple modules including a dictionary, NER, candidate generation, disambiguation, and reranking, achieving unspecified performance on TAC EDL data from 2014-2016.
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.