Undergraduate-Research Mentored Projects (2007-2011)

List of All Mentored NLP Bachelor Projects in reverse chronological order

2010-2011


+ AJEB:  Question answering system for Arabic documents. The project is planned to have three modules. Document analysis Module should analyze documents putting them in meaningful representation. Query analysis Module should understand the semantics of the questions. Answer Generation Module utilizes the extracted semantics from documents and questions for detection of the best answers for the question.


+ Story Building System:  NLP System whose goal is to transform Arabic plain text of constrained children stories into animation to serve as an interactive and exciting way for teaching children. The plain text is going be transformed to semantic form which will be transformed into a story model. Finally the story model will be used to build the animation



2008-2009



+ Intelligent Information Discovery & Processing System (IIDPS): IIDPS is mainly a NLP system able to crawl the web semantically based on specific topic, and automatically generate a report for the user summarizing the achieved information. Firstly, the crawled page passes a cleaning phase (clearing irrelevant information, e.g. tags, ADs and etc). Then document vector is created and passed to a previously trained Neural Network to determine relevancy to the trained topic(s). The documents are viewed and ranked according to the relevancy, with the most relevant paragraph viewed in the summarized report.




2007-2008

 

+ Mind Map Generator: This project serves as a novel idea in NLP applications. It enables digital technology to completely build up mind map (a widely used visual representation of information) given a plain text as input. The plain text goes through NLP-front end module; performing parsing, structural analysis, discourse analysis and word sense disambiguation. Then the Meaning Representation is built which is input to the visualization module to generate representative pictures for mind map nodes. Finally Dynamic layout allocation module, which adopts an iterative numerical approach based on Spring Model, was implemented to layout the created Mind Map on the drawing canvas.



YouTube Video