Ismail Fahmi

I am interested in: machine learning, digital library, term extraction, term variation, information extraction, semantic web, ontology.

Automatic Term Recognition Using Dependency Relation

Promotor: Prof. dr. ir. John Nerbonne
Supervisor: Dr. Gosse Bouma

Abstract
In text mining, the acquisition of new knowledge requires the recognition of terms, as they denote new information. We plan to investigate the effect of using large-scale dependency analysis on the accuracy of Automatic Term Recognition (ATR). More in particular, we want to investigate (i) the linguistic patterns that need to be defined to do for Dutch, (ii) the effect of the dependency analysis on the accuracy of ATR and (iii) how ATR can be used to boost the performance of Question Answering.

Duration: January 2004 - January 2008
Group web: IMIX Project.

Applying the Semantic Web for History: Early American Imprints, Series I

Ismail Fahmi and
Henk Ellerman (Digital library dept. of the University Library)

The SWHi (Semantic Web for History) project is aimed at integrating, combining, and deducing information about early American history, based on the Early American Imprints, Series I: Evans, 1639-1800, to assist general users or historians in exploring American history by using the new technology offered by the Semantic Web.

This project is a cooperation between the digital library department of the University Library of Groningen and the computer science department of the University of Groningen.

Duration: January 15, 2006 - January 15, 2008.
Visit the Web site.

2008

• Ismail Fahmi, Henk Ellermann, Peter Scholing and Junte Zhang, Improving Berrypicking Techniques Using Semantically Similar Information in a Historical Digital Library System. The first SIEDL Workshop / ESWC 2008. Tenerife, Spain, 2008. [PDF]
• Ismail Fahmi, Peter Scholing and Junte Zhang. (Poster) Digitally Deducing Information about the Early American History with Semantic Web Techniques. DH2008, Oulu, Finland, June 25-29, 2008.

2007

• Junte Zhang, Ismail Fahmi, Henk Ellermann, and Gosse Bouma, Mapping Metadata for SWHi: Aligning Schemas with Library Metadata for a Historical Ontology in Proceedings of the International Workshop on Collaborative Knowledge Management at WISE2007, LCNS 4832, Springer, 2007. [PDF]
• Ismail Fahmi, Gosse Bouma and Lonneke van der Plas. Using Multilingual Terms for Biomedical Term Extraction. Proceeding of the AMML workshop, RANLP 2007. [PDF]
• Ismail Fahmi, Junte Zhang, Henk Ellerman, and Gosse Bouma, SWHi System Description: A Case Study in Information Retrieval, Inference, and Visualization in the Semantic Web, E. Franconi, M. Kifer, and W. May, Proceedings of European Semantic Web Conference (ESWC) 2007, LNCS 4519, Springer. [PDF]
• Gosse Bouma, Ismail Fahmi, Jori Mur, Gertjan van Noord, Lonneke van der Plas, and Jörg Tiedemann, Linguistic Knowledge and Question Answering, To appear in Traitement Automatique des Langues (TAL). [PDF]

2006

• Fahmi, Ismail and Gosse Bouma. 2006. "Learning to Identify Definitions using Syntactic Features". Workshop of Learning Structured Information in Natural Language Applications, 11th Conference of the European Chapter of the Association for Computational Linguistics. Italy, April 2006. [PDF]
• Gosse Bouma, Ismail Fahmi, Jori Mur, Gertjan van Noord, Lonneke van der Plas, and Jörg Tiedemann, The University of Groningen at QA@CLEF 2006: Using Syntactic Knowledge for QA. [PDF]

2005

• Fahmi, Ismail. 2005. Chapter "The development of Indonesia's National Digital Library Network". In Book: Design and Usability of Digital Libraries: Case Studies in the Asia Pacific. Editor: Yin-Leng Theng and Schubert Foo, NTU Singapore. Idea Group Inc. Publishing, 2005. [author version]

2002

• Fahmi, Ismail, Ruri Muharto and Ismail Khalil Ibrahim. 2002. "Extending the OAI Protocol ast the Data Integration Framework for the Digital Library Network in the Third World". iiWAS 4th Conference, Bandung, Indonesia, September 12, 2002.
• Fahmi, Ismail. 2002. "The Indonesian Digital Library Network is Born to Struggle with the Digital Divide," ASIST Bulletin, Vol 28, No 4, April/May 2002. URL: http://www.asis.org/Bulletin/May-02/fahmi.html. December 24, 2003. Also appear in the International Information and Library Review (YIILR), Article no 191. Note: The paper has won the First Prize from the International Paper Contest, ASIST, 3-8 November 2001, Washington DC.

2001

• Fahmi, Ismail. 2001. "Delivering Distance Learning Resources Through the Indonesian Digital Library Network," Submitted to the International Symposion on Open Distance Learning, 12-14 November 2001, Yogyakarta, Indonesia.
• Fahmi, Ismail. 2001. "Mirroring Unified Metadata as the Solution for the Digital Library Network at Developing Countries," In IIWAS 2001 Proceeding, Third International Conference on Information Integration and Web-based Application & Services, September 2001, Lintz, Austria.
• Fahmi, Ismail. 2001. "Developing Digital Library Network in Indonesia," ACCESS Magazine, Asia's Newspaper on Electronic Information Product & Services, March 2001 No 36, Bangkok, Thailand. URL: http://www.igroupnet.com/access/number36/subject05.cfm.

1999

• Fahmi, Ismail. 1999. "The Library Network in Indonesia," LASIE Magazine, Library Automated System Information Exchange volume 30 no. 4, December 1999 - State Library of NSW Australia. URL: http://www.sl.nsw.gov.au/lasie/dec99/dec99.pdf.

2007

• I. Fahmi, Gosse Bouma, and Lonneke vd. Plas. 2007. Using Known Terms for Automatic Term Extraction. Computational Linguistics in Nederland (CLIN), January 12, 2007. [Slides PDF]

2006

• Fahmi, Ismail and Henk Ellermann. 2006. Semantic Web for History. Advanced Webtechnology class, November 29, 2006. [Slides PDF]
• Fahmi, Ismail and Gosse Bouma. 2006. "Learning to Identify Definitions using Syntactic Features". Workshop of Learning Structured Information in Natural Language Applications, 11th Conference of the European Chapter of the Association for Computational Linguistics. Italy, April 2006. [Slides PDF]

2005

• I. Fahmi, Gosse Bouma. 2005. Learning Medical Definition. Computational Linguistics in Nederland (CLIN), December 16, 2005. [Slides PDF].
• I. Fahmi, Henk Ellerman. 2005. Early American Imprints (Evans) on the Semantic Web. Talk at the Advanced Webtechnology class. [Slides PDF: short - long].
• I. Fahmi. 2005. Incorporating dependency relation for multi-word term extraction. TABU Dag, June 3, 2005. [Slides PDF].
• I. Fahmi. 2005. C-value method for multi-word term extraction. In seminar in Statistics and Methodology, May 23, 2005. [Slides PDF]

Term Extraction

Statistical techniques for term extraction: extracting term from a medical encyclopedia corpus using several statistical measures, e.g. frequency, c-value, dice, log likelihood, pointwise mutual information, true mutual information, t-score, and chi-squared (x2).

Learning and Searching Definitions

Ask a definition: search definitions of a concept from the Wikipedia text.

Ganesha Digital Library

GDL or Ganesha Digital Library is a web-based application for a simple digital library. It is easy to use. You can manage your electronic document, images, photos, audio, and video using GDL. Metadata is stored in the database using XML format. Digital collections are stored in a file system format.
[Download]

IsisOnline - Library Search

IsisOnline is a web based search engine for CDS/ISIS database. You can publish your CDS/ISIS database easily. Just upload the required CDS/ISIS files. No database conversion is needed. IsisOnline uses openisis as the interface between the web and the CDS/ISIS database.
[Download]

Prize: The Indonesia ICT Award 2002 on Special Category

Title: The Indonesian Digital Library Network (IndonesiaDLN)
Award from: The Ministry of Communication and Information Indonesia, and the i2bc (Indonesia Infocosm and Business Community)
Date: August 2002.
Award information:
- http://www.i2bc.org/eaward/2002/profilunggul2002.html
- http://web.idrc.ca/en/ev-22154-201-1-DO_TOPIC.html

First Prize: Award of International Paper Contest on Digital Library at Developing Countries

Title: The Indonesian Digital Library Network is Born to Struggle with the Digital Divide.
Award from: ASIST (American Society for Information Science and Technology).
URL:http://www.asis.org/Bulletin/May-02/fahmi.html
Date: November 2001
Award information: http://www.asis.org/Bulletin/May-02/sigiii.html

Project Grant: Development of Small Medium scale Enterprises information system network based on GDL (Ganesha Digital Library)

Principal Investigator: Ismail Fahmi
Year: 2000-2003
Grant from:
YLTI (Indonesian Foundation for Telecommunication and Information Research), Indonesia, Grant Number: YLTI.0./HK/PRG-MN21/2000

Project Grant: National Networked Digital Library, Indonesia

Title: Network of Digital Library of Research Reports, Thesis, and Dissertations.
Principal Investigator: Ismail Fahmi
Year: 2000-2002
Grant from:
- IDRC (International Development Research Center), Canada, CCOHS Project Number: 001.1.2
- YLTI (Indonesian Foundation for Telecommunication and Information Research), Indonesia, Grant Number: YLTI.04/HK/PRG-Lbry/2000
Final Report: http://network.idrc.ca/uploads/user-S/1036697091000112fr.htm
News: http://network.idrc.ca/ev.php?ID=4721_201&ID2=DO_TOPIC
Main sites:
- Free software Ganesha Digital Library (GDL): http://gdl.itb.ac.id
- IndonesiaDLN hub server: http://hub.indonesiadln.org

Master

Department of Computer Science, University of Groningen, Groningen, The Netherland. 2003.
Thesis: Examining Learning Algorithms for Text Classification In Digital Libraries.

Bachelor

Department of Electrical Enginneering with a major in the Telecommunication Engineering, Bandung Institute of Technology (ITB), Bandung, Indonesia. 1992-1997.