JIITA, vol. 2, no. 4, pp.176-182, Dec, 2018
An Enhanced Part-of-Speech Tagger for English
Mary Destiny M. Abellana 1), Robert R. Roxas 2,*)
1,2) Dept. of Computer Science, College of Science, University of the Philippines Cebu, Cebu City, Philippines
Abstract: This paper presents a Part-of-Speech (POS) Tagger that can accurately tag words, especially the homographs in a sentence. Our POS Tagger aims to overcome the problems we encountered when using other well-known Taggers for the English Language. Our POS Tagger uses a POS tagged corpus, which contains tag sentences that serve as the syntax as well as the semantic rules and a dictionary (POS-Word Mapping Dictionary) containing all the possible POS tags of a word. Our POS tagger scored an accuracy of ninety-six percent (96%) for our simple test, which is significantly higher than the two Taggers that we compared with. Our POS Tagger achieved the purpose of addressing the issues found in the other Taggers by correctly tagging the homographs.
Keyword: POS tagger; homograph; tagset