Evaluation Contest of Named Entity Recognition Systems for Portuguese: HAREM
Linguateca, a distributed resource center for the computational processing of Portuguese, is devoted to the evaluation of Portuguese language processing areas and systems, the creation of publicly available resources, and the providing of relevant information to the community (the so-called IRE model).
HAREM is the first evaluation contest for named entity recognition (NER) for Portuguese. The (First) HAREM call for participation was issued in September 2004, and the First HAREM came to include two evaluation events: the first one took place from 14 to 16 February, 2005, with 10 participants (see complete list). The second event (dubbed MiniHAREM) happened from 3 to 5 April, 2006.
The First HAREM is now concluded, and this site is no longer updated. Yet, a Second HAREM is scheduled to take place in 2007-8. For further information, please visit the HAREM site.
Note: HAREM stands for HAREM é uma Avaliação de Reconhecedores de Entidades Mencionadas (roughly, "HAREM is a NER Evaluation").
Publications on the First HAREM
So far, we have the following publications in English about the First HAREM:
- Diana Santos. "HAREM: the first evaluation contest for Named Entity Recognition in Portuguese". Presentation at IST (Lisbon, Portugal, 24 February 2006). Slides
- Diana Santos & Nuno Cardoso. "A Golden Resource for Named Entity Recognition in Portuguese". In Renata Vieira, Paulo Quaresma, Maria da Graça Volpes Nunes, Nuno J. Mamede, Cláudia Oliveira & Maria Carmelita Dias (eds.), 7th Workshop on Computational Processing of Written and Spoken Language (PROPOR'2006) (Itatiaia, RJ, 13-17 de Maio de 2006), Springer, pp. 69-79. pdf Slides
- Nuno Seco, Diana Santos, Rui Vilela & Nuno Cardoso. "A Complex Evaluation Architecture for HAREM". In Renata Vieira, Paulo Quaresma, Maria da Graça Volpes Nunes, Nuno J. Mamede, Cláudia Oliveira & Maria Carmelita Dias (eds.), 7th Workshop on Computational Processing of Written and Spoken Language (PROPOR'2006) (Itatiaia, RJ, 13-17 de Maio de 2006), Springer, pp. 260-263. pdf Poster
- Diana Santos, Nuno Seco, Nuno Cardoso & Rui Vilela. "HAREM: An Advanced NER Evaluation Contest for Portuguese". In Nicoletta Calzolari, Khalid Choukri, Aldo Gangemi, Bente Maegaard, Joseph Mariani, Jan Odjik & Daniel Tapias (eds.), Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC'2006) (Genoa, Italy, 22-28 May 2006), pp. 1986-1991. pdf
- Diana Santos & Nuno Cardoso (eds.). Reconhecimento de entidades mencionadas em português: Documentação e actas do HAREM, a primeira avaliação conjunta na área. Linguateca. 2007. ISBN: 978-989-20-0731-1. 413 pages (some chapters in English), http://www.linguateca.pt/LivroHAREM
Golden Collection
The Golden colections used on the First HAREM are available to download.