A Comparative Evaluation of a New Unsupervised Sentence Boundary Detection Approach on Documents in English and Portuguese

Abstract. In this paper, we describe a new unsupervised sentence boundary detection system and present a comparative study evaluating its performance against different systems found in the literature that have been used to perform the task of automatic text segmentation into sentences for English and Portuguese documents. The results achieved by this new approach were as good as those of the previous systems, especially considering that the method does not require any additional training resources.

• Type: Conference
• Year: 2006
• Where: CICLING
• Authors: Jan Strunk, Carlos Nascimento Silla Jr., Celso A. A. Kaestner
• Keywords: Additional Training Resources, Automatic Text Segmentation, Boundary Detection, CICLING 2006, Natural Language Processing