Event Extraction in Persian Texts By Learning Methods

Please enable javascript in your browser.

Ershad, Mehdi | 2015

497 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 47664 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Ghasem Sani, Gholamreza
Abstract:
Event Extraction in Texts is one of the main challenges of Natural Language Processing. Event extraction is one of necessary components of question answering, summarization and information extraction systems. The purpose of this project has been the design and implementation of different statistical methods for event extraction in Persian and also correcting and expanding an existing corpus named PresTimeBank. The new system is composed of a preliminary rule based module that annotates events and find their features based on a predefined set of rules. The result of this stage is then revised in a subsequent manual annotation process. The output is a corpus that is compliant with the ISO TimeML standard. This project is the first attempt to tackle the event extraction challenge in Persian using statistical methods. Support vector machines and conditional random fields have shown to have the best results. These results have been compared with that of a previous work, which was a fully rule based approach, The results show an acceptable improvement
Keywords:
Natural Language Processing ; Information Extraction ; Event Extraction ; Persian Text Processing

No TOC