A Grammatically Structured Noun Phrase Extractor for Vietnamese
Hoai-Duc Tuan-Nguyen, Bao-Quoc Ho, Tuan-Dung Bui, Minh-Chau Hoang · 2012
Noun phrase (NP) extraction is a vital part of any Natural Language Processing (NLP) system. However, it would be much better if the system can also parse the grammar structure of the extracted NPs. Grammatically structured NP (GSNP) is helpful in many research fields (Conceptual Indexing, Syntactic variant generating, Nested NP identifying, etc). This paper introduces a system that extracts NPs from Vietnamese Documents and parses each NP into a tree representing its grammar structure. These trees, in one hand, can be saved as XML documents, and in the other hand, can be loaded from these XML documents by some particular Java classes.