Author :
Perkins, A. Louise ; Gunichetty, Haritha ; Pachva, Srilekha ; Rishel, Tom ; Walley, Bryant ; Yasa, Chethana ; Satya, Uma
Author_Institution :
Sch. of Comput., Univ. of Southern Mississippi, Hattiesburg, MS, USA
Abstract :
In this paper we propose a method for identifying the semantic context of segments of text within a larger document. Our method is based on an extension of Chomsky´s x-bar theory. We adapt the x-bar concept of headedness to a coarser granularity of text, such as paragraphs. Using this method, which we call P-bar, we map a set of vocabulary domains to a unique semantic context. Using a rule-based error-driven algorithm, we show that this approach has significant context identification skill within a Rayleigh-Ritz like approximation framework.
Keywords :
approximation theory; knowledge based systems; natural language processing; text analysis; P-bar theory; Rayleigh-Ritz like approximation framework; coarser granularity; headedness; large-documents; rule-based error-driven algorithm; semantic context identification; text segments; vocabulary domains; x-bar theory; Accuracy; Approximation methods; Context; Dictionaries; Natural language processing; Semantics; Vocabulary; Context identification; natural language processing; p-bar; partext; x-bar;
Conference_Titel :
Innovative Computing Technology (INTECH), 2015 Fifth International Conference on
Conference_Location :
Galcia
DOI :
10.1109/INTECH.2015.7173481
