Title :
Low Resources Prepositional Phrase Attachment
Author :
Nalmpantis, Pavlos ; Kalamatianos, Romanos ; Kordas, Konstantinos ; Kermanidis, Katia
Author_Institution :
Dept. of Inf., Ionian Univ., Corfu, Greece
Abstract :
Prepositional phrase attachment is a major disambiguation problem when it´s about parsing natural language, for many languages. In this paper a low resources policy is proposed using supervised machine learning algorithms in order to resolve the disambiguation problem of Prepositional phrase attachment in Modern Greek. It is a first attempt to resolve Prepositional phrase attachment in Modern Greek, without using sophisticated syntactic annotation and semantic resources. Also there are no restrictions regarding the prepositions addressed, as is common in previous approaches.
Keywords :
learning (artificial intelligence); natural language processing; disambiguation problem; low resources prepositional phrase attachment; natural language; supervised machine learning; Classification algorithms; Classification tree analysis; Feature extraction; Machine learning; Machine learning algorithms; Support vector machine classification; Syntactics; Decision Trees; Modern Greek; PP attachment; Supervised learning;
Conference_Titel :
Informatics (PCI), 2010 14th Panhellenic Conference on
Conference_Location :
Tripoli
Print_ISBN :
978-1-4244-7838-5
DOI :
10.1109/PCI.2010.34
