Title:    Open-Domain Textual Question Answering

Speakers: Professor Sanda Harabagiu
	  Department of Computer Science and
          Human Language Technology Research Institute
          University of Texas at Dallas
	  Richardson, TX 75083-0688, USA 
          Phone: (972) 883-4654
          email: sanda@cs.utdallas.edu

          Professor Dan Moldovan
	  Department of Computer Science and
	  Human Language Technology Research Institute
          University of Texas at Dallas
	  Richardson, TX 75083-0688, USA 
          Phone: (972) 883-4838
          email: moldovan@utdallas.edu


Summary: Question Answering (QA) is a fast growing area of research with 
	 tremendous commercial potential. The problem of QA  is to find  
	 answers to open-domain questions by searching a large collection 
	 of documents. Unlike Internet search engines, QA systems provide 
	 short, relevant answers to questions.    

	 The recent explosion of information available on the World Wide Web 
	 makes question answering  a compelling framework for finding 
	 information that closely matches user needs. Due to the fact that 
	 both questions and answers are expressed in natural language, QA
	 methodologies deal with language ambiguities and incorporate NLP
	 techniques. 

	 Ideal QA systems should have good dialog understanding, rich
	 knowledge bases and quality text mining methods. They will certainly
	 incorporate common sense reasoning methods and use good approximations
	 of world knowledge.  Until we have these more advanced tools, we can
	 approximate QA with NLP enhancements of IR and IE techniques. 


	 The tutorial presents a survey of the most performant open-domain 
	 QA systems architectures  and the basic techniques employed 
	 to build them. Topics include: answer taxonomies, answer processing, 
	 document retrieval, answer extraction and ranking, accuracy 
	 performance and speed performance. 


Course Outline:

        1. Introduction to the problem of textual Question Answering (QA) and
	   examples of several QA taxonomies.
	2. Survey of prominent researches in QA from the past and their 
	   influence on current QA research.
	3. Architecture of QA systems, describing the question processing,
	   document processing, answer extraction and ranking.
	4. Techniques that enable advanced QA: keyword selection, paragraph
	   indexing, answer justification and interactive QA through dialogs
	5. Ontological and linguistic resources for building accurate QA
	   systems: Named Entity taggers, probabilistic parsers, WordNet
	   and its extensions
	6. Answering questions by exploiting the redundant information on the
	   World Wide Web.
	7. A Special Case: Anwering definition questions.
	8. Answering questions in context and deriving question implications.
	9. Open issues in QA: Brief survey of current research issues in 
	   Advanced QA e.g. multilinguality, context, rapid knowledge 
	   acquisition from texts and other sources.
        10. Lastly we would like to discuss with participants the future
            of this research field.

Bio:     Professor Sanda Harabagiu

         Research interests: question answering, reference resolution,
		  discourse and dialog processing, lexico semantics.

         Areas of expertise: natural language processing.

         ------------

         Professor Dan Moldovan

         Research interests: Question answering, knowledge acquisition
	     from texts, word sense disambiguation, parallel and distributed
	     processing.


         Areas of expertise: aritificial intelligence, natural language
	     processing.