Automatic repairing of web wrappers

ABSTRACT

We study the problem of automatic repairing of wrappers for Web information providers. Majority of Web wrappers use "hooks'' or "landmarks'' to find and extract relevant information from Web pages and such wrappers often become inoperable when the page structure is changed. The solution we propose in this paper extends conventional forward wrappers with alternative classifiers built using content features of extracted information and wrappers processing pages backward. We report some preliminary results of the information extraction recovery and wrapper repairing for a set of real Web provider changes.

REFERENCES

• 1: Denis Breddet and Bruno Roustant. Java IWrap: Wrapper Induction by Grammar Learning. Master's thesis, ENSIMAG, Grenoble, France, 2000.
• 2: Boris Chidlovskii , Jon Ragetli , Maarten de Rijke, Wrapper Generation via Grammar Induction, Proceedings of the 11th European Conference on Machine Learning, p.96-108, May 31-June 02, 2000
• 3: Boris Chidlovskii, Wrapping Web Information Providers by Transducer Induction, Proceedings of the 12th European Conference on Machine Learning, p.61-72, September 05-07, 2001
• 4: M. Harries and K. Horn. Learning stable concepts in domains with hidden changes in context. In Learning in context-sensitive domains Workshop, 13th International Conference on Machine Learning,, 1996.
• 5: C.-N. Hsu and C.-C. Chang. Finite-state transducers for semi-structured text mining. In Proceedings of IJCAI-99 Workshop on Text Mining: Foundations, Techniques and Applications, 1999.
• 6: Craig A. Knoblock, Kristina Lerman, Steven Minton, and Ion Muslea. Accurately and reliably extracting data from the web: A machine learning approach. IEEE Data Engineering Bulletin, 23(4):33-41, 2000.
• 7: Nicholas Kushmerick, Wrapper induction: efficiency and expressiveness, Artificial Intelligence, v.118 n.1-2, p.15-68, April 2000 [doi>10.1016/S0004-3702(99)00100-9]
• 8: Nicholas Kushmerick, Wrapper verification, World Wide Web, v.3 n.2, p.79-94, 2000 [doi>10.1023/A:1019229612909]
• 9: Thomas M. Mitchell, Machine Learning, McGraw-Hill Higher Education, 1997
• 10: Ion Muslea , Steve Minton , Craig Knoblock, A hierarchical approach to wrapper induction, Proceedings of the third annual conference on Autonomous Agents, p.190-197, April 1999, Seattle, Washington, United States [doi>10.1145/301136.301191]
• 11: Gerhard Widmer , Miroslav Kubat, Learning in the presence of concept drift and hidden contexts, Machine Learning, v.23 n.1, p.69-101, April 1996 [doi>10.1023/A:1018046501280]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.2 Design Methodology
          Subjects: Classifier design and evaluation

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.4 Systems and Software
          Subjects: Performance evaluation (efficiency and effectiveness)
      H.3.5 On-line Information Services
          Subjects: Web-based services

General Terms:
Design, Experimentation, Performance