Vietnamese proper noun recognition
Chau Q. Nguyen, Uyen Phan, Tru Hoang Cao · 2006
Recognition of proper noun is one of complex problems in Vietnamese natural language processing (NLP). This paper introduces, first, an approach for recognizing of Vietnamese proper noun. Second, it introduces NLP techniques that we propose to analyze Vietnamese texts, focusing on advanced word segmentation which accounts for a number of complex linguistic phenomena as well as pre-tagging, part-of- speech (POS) tagging, and post-tagging tasks for proper noun recognition. Finally, the paper discusses the results of several experiments that have been performed to study the impact of the strategy chosen for the recognition of Vietnamese proper nouns and the further works we intend to deal with. Index_Terms— Vietnamese, natural language processing, word segmentation, tagger, tagset, part-of-speech, POS tagging, text corpus, pre-tagging, post- tagging, corpus, syntax, context of texts, proper names, proper noun recognition.