Information Extraction and Text MiningLectures: 24 h (seminars and lectures)Recommended forGraduate and doctoral students. The course was last given: NeverThe course runs: Fall 2001GoalsTo provide an overview of the field of Information Extraction, including concepts and methods that primarily has a Language Engineering perspective. The course will also cover fundamental issues in Text Mining and Document Summarisation. PrerequisitesGraduate student, with some knowledge of linguistics. OrganizationGuded discussions based on reading of prepared material. Case studies and examples will be used to illustrate the practical application of the main concepts and methods. ContentsIE can be seen as taking one step further compared to Information Retrieval (IR) in that not only the relevant documents should be found, but the process moves on to first single out passages, or extracts from documents, which contain the desired pieces of information, and second, turns them into structured information that is more readily digested and analyzed. IE requires a number of separate Language Engineering techniques that are used together; i.e., POS-tagging, functional and sense disambiguation, pronoun resolution, etc. LiteratureCarbonell, J.G., J. Siekmann & Maria T. Pazienza (eds.). Information Extraction : Towards Scalable, Adaptable Systems, Springer Verlag, Lecture Notes in Artificial Intelligence, 1999. + selected journal and conference articles. TeachersMagnus Merkel ExaminerMagnus Merkel ScheduleFall 2001 ExaminationActive participation (presenting articles) and written paper. Credit4 credits |
Page responsible: Anne Moe