Difference between revisions of "Web Browsing for Visually Impaired People"


Line 13: Line 13:
== Speaker ==
== Speaker ==
* Gäel Dias (Universidade da Beira Interior)
* [http://www.di.ubi.pt/~ddg Gäel Dias (Universidade da Beira Interior)]
== Abstract ==
== Abstract ==

Revision as of 17:08, 27 November 2006

Gäel Dias
Gäel Dias was gratduated from the University of Orléans (France) in Computer Science and Management (Maîtrise d'Informatique Appliquée à la Gestion). I have a Master Degree in the specific field of Languages, Programming and Translation (DEA Langages, Programmation et Traduction) from the Laboratoire d'Informatique Fondamentale d'Orléans (LIFO) in France. And, I have PhD in Natural Language Processing (especifically in Automatic Extraction of Collocations from Corpora) from the New University of Lisbon (Portugal) in collaboration with the Laboratoire d'Informatique Fondamentale d'Orléans. Now, he is an Assistant Professor and Vice Dean of the Department of Computer Science of the University of Beira Interior in Covilhã by the Portuguese mountains where I teach all subjects related to Artificial Intelligence and System Analysis. I am also the coordinator of the professional activities of the course on Software and Systems (Sponsored by Microsoft) of the Department of Computer Science. He also works as researcher at the Centre of Mathematics of the University of Beira Interior and I am an Invited Researcher at the L2F Group of INESC-ID in Lisbon (Portugal). He has the Erdös Number 5 classification (Erdös number project). He also is responsible for the Centre of Human Language Technology and Bioinformatics (HULTIG) of the University of Beira Interior. And finally, he is a member of the Association for Computational Linguistics (ACL), a member of the French Association for Natural Language Processing (ATALA) and a member of the Portuguese Association of Artificial Intelligence (APPIA). (www.di.ubi.pt/~ddg)


  • December 05, 2006
  • Location: Room 336



Although a lot has been done for Visually Impaired People to access information with Braille screens, Braille keyboards, Braille PDAs and Text-to-Speech interfaces, very little has been made to reduce the amount of information they have to deal with. In this presentation, we propose an automatic summarization system to ease web browsing for visually impaired people on handheld devices. In particular, we introduce different efficient methods for summarizing parts of web pages in real-time and include Text-to-Speech facilities. Two main approaches have already been proposed in the literature. First, some methodologies such as [1] [3] use simple summarization techniques to produce results in real-time but clearly lack linguistic treatment for reliable content visualization. Second, some works apply linguistic processing and rely on ad hoc heuristics [2] to produce compressed contents but can not be used in real-time environment. As a consequence, we propose a new architecture for summarizing Semantic Textual Units [1] based on efficient algorithms for linguistic treatment that allow real-time processing and deeper linguistic analysis of web pages, thus allowing quality content visualization. In this talk, we will also present the VIP-ACCESS project and the different talks that the members of the Centre for Human Language Technology and Bioinformatics will deliver.

[1] O. Buyukkokten, H. Garcia-Molina and A. Paepcke. Seeing the Whole in Parts: Text Summarization for Web Browsing on Handheld Devices. In Proc. of the 10th International World Wide Web Conference. (2000).

[2] P. Gomes, S. Tostão, D. Gonçalves and J. Jorge. Web-Clipping: Compression Heuristics for Displaying Text on a PDA. In Proc. of 3rd Workshop on Human Computer Interaction with Mobile Devices. (2001).

[3] C. Yang and F.L. Wang. Fractal Summarization for Mobile Devices to Access Large Documents on the Web. In Proc. of the International World Wide Web Conference. (2003).