832
views
0
recommends
+1 Recommend
1 collections
    0
    shares

      Celebrating 65 years of The Computer Journal - free-to-read perspectives - bcs.org/tcj65

      scite_
       
      • Record: found
      • Abstract: found
      • Conference Proceedings: found
      Is Open Access

      Combining Evidence with Logic and Preferences to Learn Relations from Structured Few Sparse Textual Data

      proceedings-article
      ,
      Third International Symposium on Innovation and Information and Communication Technology (ISIICT 2009) (ISIICT)
      Innovation and Information and Communication Technology (ISIICT 2009)
      15 - 17 December 2009
      Structural Constraints, Analysis of Textual Patterns, Learning from Few Examples, Interclass Relationships, Sparse Textual Data
      Bookmark

            Abstract

            In the literature, it is commonly believed that learning from few data problem can be resolved by using classifiers that consider interclass relationships. In this work, we will adopt this point of view in learning from few sparse textual data, essentially, by considering the sparseness of the latter as a good support for inducing theories about generalization. Therefore, we opt for an inductive approach based on combining: evidence-based analysis of patterns, logic and preferences. More precisely, we are interested in supervised learning of biomedical articles by exploiting a multi-scale hybrid description and constrained pattern-based data mining techniques. Unlike existing works, we will highlight the relevance of the absence/weakness of patterns and we will associate to their absence a semantic value compared to their presence. The main characteristic of our approach is that of considering local and global contexts, which connect textual data by introducing regret ratio measures and generalized exclusive patterns in order to avoid a crisp effect between the absence and presence of patterns. Experimental results show the effectiveness of our approach.

            Content

            Author and article information

            Contributors
            Conference
            December 2009
            December 2009
            : 14-27
            Affiliations
            [0001]Paragraph Laboratory EA 384

            Paris 8 University

            2, rue de la liberté 93000

            Saint Denis – France
            Article
            10.14236/ewic/ISIICT2009.2
            665b7189-e6af-4245-95c3-e48fe665ab23
            © Nadia Zerida et al. Published by BCS Learning and Development Ltd. Third International Symposium on Innovation and Information and Communication Technology (ISIICT 2009), Philadelphia University, Amman, Jordan

            This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

            Third International Symposium on Innovation and Information and Communication Technology (ISIICT 2009)
            ISIICT
            3
            Philadelphia University, Amman, Jordan
            15 - 17 December 2009
            Electronic Workshops in Computing (eWiC)
            Innovation and Information and Communication Technology (ISIICT 2009)
            History
            Product

            1477-9358 BCS Learning & Development

            Self URI (article page): https://www.scienceopen.com/hosted-document?doi=10.14236/ewic/ISIICT2009.2
            Self URI (journal page): https://ewic.bcs.org/
            Categories
            Electronic Workshops in Computing

            Applied computer science,Computer science,Security & Cryptology,Graphics & Multimedia design,General computer science,Human-computer-interaction
            Structural Constraints,Interclass Relationships,Analysis of Textual Patterns,Sparse Textual Data,Learning from Few Examples

            Comments

            Comment on this article