flKeynote Speakers

First keynote speaker

Dr Horacio Rodriguez

 

Research Group on Natural Language Processing

Technical University of Catalonia (UPC), Barcelona, Spain

 

 

"Arabic Wordnet as a free resource: past, present and the future"

ppt


The Arabic WordNet ontology (AWN) is among the most interesting Arabic resources available for Arabic NLP researchers. The AWN ontology is a free lexical resource for modern standard Arabic. Arabic WordNet has been built along the last years following the EuroWordNet methodology of encoding a set of base concepts while maximizing compatibility across wordnets. AWN is based on the design and contents of Princeton WordNet and it can be mapped onto it as well as a number of other WordNets, enabling translation on the lexical level to and from dozens of other languages. AWN is also connected to SUMO (Supper Upper Merged Ontology). The SUMO is an upper level ontology which provides definitions for general-purpose terms and acts as a foundation for more specific domain ontologies. It contains about 2000 concepts.
Arabic WordNet currently consists of 11,269 synsets (7,960 nominal, 2,538 verbal, 661 adjectival, and 110 adverbial), containing 23,481 Arabic expressions. AWN is in a continuing extension, using different methods, to cover as large as possible the Arabic language.

 


Horacio Rodriguez got a PhD degree in Computer Science, UPC, 1989. He is Graduate in Sciences (Physics), UB, 1977 and Industrial Engineer, UPC, 1970.

He has a full time permanent position as Associate Professor at UPC (Software, LSI, department), since 1989. Previously he spent 15 years working in several Spanish companies and part time at the university.

H. Rodriguez has lead several Spanish, European and USA funded projects, as EuroWordNet (1996-1999), ITEM (1996-1999), Catalan WordNet (1997-1999), Aliado(2002-2005), Arabic WordNet (2005-2007) and participated in many others, as ACQUILEX (1989-1992), ACQUILEX II (1993-1995), NAMIC (1999-2001), HERMES (2001-2003), FAME(2001-2004), Text/Mess(2006-2009) among others (see http://www.lsi.upc.es/~nlp/ for details). He has advised 10 PhD theses in the area of NLP. He has a huge number of publications in journals and international conferences.

His research interests are Natural Language Processing (both resources and tools) and Artificial Intelligence methods and tools.
______________________________________________________________________

 

Second keynote speaker


Dr Khalid Shaalan Dr Khaled Shaalan

                      Khaled[at]buid.ac.ae


The Faculty of Informatics, The British University in Duabi, UAE


"Rule-based approach in Arabic NLP: Tools, Systems and Resources" ppt

A rule-based approach is a traditional natural language processing approach. It is based on solid linguistic knowledge. The characteristics of a rule-based approach are: 1) Has a strict sense of well-formedness in mind, 2) Imposes linguistic constraints to satisfy well-formedness, 3) Allows the use of heuristics (such as a verb cannot be preceded by a preposition), and 4) Relies on hand-constructed rules that are to be acquired from language specialists rather than automatically trained from data. The advantages of this approach are that it is easy to incorporate domain knowledge and heuristic rules into the linguistic knowledge which provide highly accurate results for the natural language processing task. The disadvantage of this approach is that it is not easy to obtain high coverage (completeness) of the linguistic knowledge. However, it achieves good results for limited domain for which grammars were specifically developed. The rule-based approach has successfully been used for developing tools, systems and resources. Arabic tools based on this approach include, morphological analyzers, parsers, morphological generators, syntactic generators. Arabic systems based on this approach include, machine translation, named entity recognition, and intelligent tutoring systems.

Dr Khaled Shaalan is a Professor at the Faculty of Computers & Information, Cairo University, Egypt. He is on secondment, Senior Lecturer, to the Faculty of Informatics, The British University in Dubai, UAE. He is also an Honorary Fellow at the University of Edinburgh, UK. Khaled holds a PhD from Cairo University, jointly with the Swedish Institute of Computer Science, Sweden. Both his teaching and research are related to language engineering and knowledge engineering.

He is particularly interested in developing tools and applications for both knowledge-based systems and Arabic language processing. Khaled has led extensive research on machine translation, information extraction, and agricultural expert systems. Khaled has about 20 years of experience in developing tools, systems and applications for Arabic natural language processing using the rules-based approach. He has published in leading international journals such as IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE), Expert System with Applications (ESWA), New Review of Applied Expert Systems, International Journal of Computer Processing of Oriental Languages (IJCPOL), Journal of the American Society for Information Science and Technology (JASIST), and Software Practice and Experience (SPE). Khaled has published his research in many reputed international conferences related to artificial intelligence and language processing. He is currently leading the Arabic natural language processing research group at The British University in Dubai.