Persian Grammar Induction Using Unsupervised Data Oriented Parsing

Please enable javascript in your browser.

Mesgar, Hassan | 2011

493 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 42908 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Ghassem Sani, Gholamreza
Abstract:
Automatic grammar induction is one of attractive research topics in natural language processing field. Automatic grammar induction methods can be categorized into three main groups of supervised, semi-supervised and unsupervised methods based on the type of training data that they need. Unsupervised methods are more difficult than two other. Data Oriented Parsing (DOP) is one of successful methods in unsupervised group. This method has been trained by some examples of language as same as child, then it parses new sentences based on its training knowledge. The aim of this project is finding and improving performance of UDOP method on Persian language as a Free Word Order language. Results of experiments show that performance of unsupervised data oriented parsing had degraded on Persian language
Keywords:
Natural Language Processing ; Unsupervised Learning ; Grammar Induction ; Data Oriented Parsing

No TOC