TagPro

TagPro is a statistical Part of Speech (PoS) tagger. It marks each word in a text with a PoS (e.g. noun, verb, adjective, etc.), according to a predefined tagset (i.e. the ELRA tagset for Italian and the BNC tagset for English). In addition to local features (e.g. orthographical characteristic of the word, affixes and suffixes), TagPro also uses a set of gazetteers of proper names.

Algorithm: TagPro uses Yamcha for feature extraction and SVM as a classification algorithm.

Resources: Data used for the PoS Tagging Task at Evalita 2007 (Italian).

Evaluation benchmark: PoS Tagging at Evalita 2007 (Italian).

Reference:

Emanuele Pianta and Roberto Zanoli. TagPro: A System for Italian PoS Tagging Based on SVM. Intelligenza Artificiale – numero speciale su Strumenti per l’elaborazione del linguaggio naturale per l’italiano EVALITA 2007, vol. 4, no. 2, pp. 8-9, Associazione Italiana per l’Intelligenza Artificiale, 2007.