SIGARRA News Corpus NER Models for OpenNLP, Stanford CoreNLP, spaCy, NLTK

Pre-trained models for named entity recognition in Portuguese, using the following entity classes: Hora (Hour), Evento (Event), Organizacao (Organization), Curso (Course), Pessoa (Person), Localizacao (Location), Data (Date) and UnidadeOrganica (Organic Unit).

데이터와 리소스

open-nlpZIP
NER models for OpenNLP, for the SIGARRA News Corpus, with the best individual...
탐색
- 추가 정보
- 다운로드
stanford-corenlpZIP
NER models for Stanford CoreNLP, for the SIGARRA News Corpus, with the best...
탐색
- 추가 정보
- 다운로드
spacyZIP
NER models for spaCy, for the SIGARRA News Corpus, with the best individual...
탐색
- 추가 정보
- 다운로드
nltkZIP
NER models for NLTK, for the SIGARRA News Corpus, with the best individual...
탐색
- 추가 정보
- 다운로드

추가 정보

필드	값
소스	https://rdm.inesctec.pt/dataset/cs-2017-004
저자	André Pires
최종 업데이트	11월 15, 2018, 10:38 (UTC)
생성됨	6월 13, 2017, 16:16 (UTC)
dc.Coverage.Spatial	Portugal
dc.Coverage.Temporal	2016-12-14 to 2017-03-01
dc.Date	2017
dc.Format	*.zip
dc.Format.Extent	80MB
dc.Language	PT
dc.Publisher	INESC TEC
dc.Relation	Master´s thesis: PIRES, André (2017).Named entity recognition on Portuguese web text. Porto: Faculdade de Engenharia da Universidade do Porto. http://hdl.handle.net/10216/106094
dc.Type	Serialized Named Entity Recognition Models