A Machine Learning Approach to Portuguese Clause Identification

Abstract. In this work, we apply and evaluate a machine-learningbased system to Portuguese clause identification. To the best of our knowledge, this is the first machine-learning-based approach to this task. The proposed system is based on Entropy Guided Transformation Learning. In order to train and evaluate the proposed system, we derive a clause annotated corpus from the Bosque corpus of the Floresta Sint

• Type: Journal
• Year: 2010
• Where: PROPOR
• Authors: Eraldo R. Fernandes, Cícero Nogueira dos Santos, Ruy Luiz Milidiú
• Keywords: Automatic State-of-the-art Tagger, Bosque Corpus, Languages, PCL Feature, PROPOR 2010