Machine Learning Algorithms for Portuguese Named Entity Recognition

Abstract

"Named Entity Recognition (NER) is an important task in Natural Language Processing. It provides keyfeatures that help on more elaborated document management and information extraction tasks. In thispaper, we propose seven machine learning approaches that use HMM, TBL and SVM to solve PortugueseNER. The performance of each modeling approach is empirically evaluated. The SVM-based extractor showsa 88:11% F-score, which is our best observed value, slightly better than TBL. This is very competitive whencompared to state-of-the-art extractors for similar Portuguese NER problems. Our HMM has reasonableprecision and accuracy and does not require any expert knowledge. This is an advantage for our HMM overthe other approaches. The experimental results suggest that Machine Learning can be useful in PortugueseNER. They also indicate that HMM, TBL and SVM perform well in this natural language processing task"