Web proceedings papers


Arta Misini , Ercan Canhasi and Samedin Krrabaj


This paper is about computational processing of the natural language, and the goal of this study is to provide an appropriate method for syntactic parsing of Albanian. We describe the prior work by ana- lyzing the current state of the field and presenting various algorithms used for parsing, using a hand-tagged corpus to build a model for the syntactic parser. Parsing is the most proper approach to identify the syntactic structure that is useful in determining the meaning of a sentence. Research has shown that English language parsers are not useful in analyzing the sen- tences in Albanian because of some morphological, syntactic, and gram- matical differences. The algorithm splits the sentences into parts of speech and analyzes these sentences using the natural languageā€™s syntactic rules. We discuss the methodology and approaches for designing and implementing the parsing methods. Then, we describe the results of our research within these directions.


Natural Language Processing, Syntactic Parsing, SentenceĀ· Phrase, Part of Speech, Tagging, Grammar, Rule