期刊名称：Romanian Conference on Human-Computer Interaction
印刷版ISSN：2344-1690
出版年度：2017
卷号：RoCHI 2017
页码：163-168
语种：English
出版社：Matrix ROM
摘要：In this article we extend our previous work [3] dedicated to developing an automatic method for generating and applying syntactic patterns intended to recognize noun phrases. The intended scope of our studies is to automatically detect dependency relations within noun phrases exploiting some syntactic information of the phrases’ words. The patterns are extracted from a corpus that has been automatically annotated for token and sentence limits, part of speech and noun phrases and manually annotated for dependency relations between words. The patterns have been generalized in order to cover more instances that were present in the corpus and to reduce the size of the grammar. In this paper we refine the syntactic patterns by considering not only the two terms of the dependency relation but also the terms surrounding these two that will be treated as contexts: left, middle, right depending on their position from the dependency terms
