ABSTRACT
We address the problem of academic conference homepage understanding for the Semantic Web. This problem consists of three labeling tasks - labeling conference function pages, function blocks, and attributes. Different from traditional information extraction tasks, the data in academic conference homepages has complex structural dependencies across multiple Web pages. In addition, there are logical constraints in the data. In this paper, we propose a unified approach, Constrained Hierarchical Conditional Random Fields, to accomplish the three labeling tasks simultaneously. In this approach, complex structural dependencies can be well described. Also, the constrained Viterbi algorithm in the inference process can avoid logical errors. Experimental results on real world conference data have demonstrated that this approach performs better than cascaded labeling methods by 3.6% in F1-measure and that the constrained inference process can improve the accuracy by 14.3%. Based on the proposed approach, we develop a prototype system of use-oriented semantic academic conference calendar. The user simply needs to specify what conferences he/she is interested in. Subsequently, the system finds, extracts, and updates the semantic information from the Web, and then builds a calendar automatically for the user. The semantic conference data can be used in other applications, such as finding sponsors and finding experts. The proposed approach can be used in other information extraction tasks as well.
- Auer, S., Dietzold, S., and Riechert, T. OntoWiki - A Tool for Social, Semantic Collaboration. In Proc. of ISWC, 2006. Google ScholarDigital Library
- Cai, D., Yu, S., Wen, J., and Ma, W. Block-based Web Search. In Proc. of SIGIR, 2004, 456--463. Google ScholarDigital Library
- Ciravegna, F. (LP)2 An Adaptive Algorithm for Information Extraction from Web-related Texts. In Proc. of the IJCAI-2001 Workshop on Adaptive Text Extraction and Mining, Seattle, USA, 2001.Google Scholar
- Ciravegna, F., Dingli, A., Iria, J., and Wilks, Y. Multi-strategy Definition of Annotation Services in Melita, In Proc. of ISWC'2003 Workshop on Human Language Technology for the Semantic Web and Web Services, 2003, 97--107.Google Scholar
- Collins, M. Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms. In Proc. of EMNLP, 2002. Google ScholarDigital Library
- Cortes, C. and Vapnik, V. Support Vector Networks. Machine Learning, 1995, 20: 273--297. Google ScholarDigital Library
- Cowell, R., Dawid, A., Lauritzen, S., and Spiegelhalter, D. Probabilistic Networks and Expert Systems. Springer-Verlag, New York, 1999. Google ScholarDigital Library
- Cox, C., Nicolson, J., Finkel, J., and Manning, C. Template Sampling for Leveraging Domain Knowledge in Information Extraction. In PASCAL Challenges, 2005.Google Scholar
- Gandon, F., and Sadeh, N. A Semantic eWallet to Reconcile Privacy and Context Awareness. In Proc. of ISWC, 2003.Google Scholar
- Ghahramani, Z. and Jordan, M.I. Factorial Hidden Markov Models. Machine Learning, 1997, 29: 245--273. Google ScholarDigital Library
- Hammersley, J. and Clifford, P. Markov fields on Finite Graphs and Lattices. 1971.Google Scholar
- He, X., Zemel, R., and Carreira-Perpiñán, M. Multiscale Conditional Random Fields for Image Labeling. In Proc of CVPR, 2004, 695--702. Google ScholarDigital Library
- Ireson, N., Ciravegna, F., Califf, M. E., Freitag, D., Kushmerick, N., and Lavelli, A. Evaluating Machine Learning for Information Extraction. In Proc. of the 22nd International Conference on Machine Learning, 2005, 345--352. Google ScholarDigital Library
- Kristjansson, T., Culotta, A., Viola, P., and McCallum, A. Interactive Information Extraction with Constrained Condition Random Fields. In Proc of AAAI, 2004, 412--418. Google ScholarDigital Library
- Lafferty, J., McCallum, A., and Pereira, F. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In Proc. of ICML, 2001, 282--289. Google ScholarDigital Library
- Lazarinis, F. Combining Information Retrieval with Information Extraction for Efficient Retrieval of Calls for Papers. In Proc. of IRSG, 1998. Google ScholarDigital Library
- Li, Y., Bontcheva, K., and Cunningham, H. Using Uneven Margins SVM and Perceptron for Information Extraction. In Proc. of CoNLL, 2005. Google ScholarDigital Library
- Liu, D. and Nocedal, J. On the Limited Memory BFGS Method for Large Scale Optimization. Mathematical Programming, 1989, 503--528. Google ScholarDigital Library
- McCallum, A., Freitag, D., and Pereira, F. Maximum Entropy Markov Models for Information Extraction and Segmentation. In Proc. of ICML, 2000, 591--598. Google ScholarDigital Library
- Payne, T., Singh, R., and Sycara, K. Browsing Schedules - an Agent-Based Approach to Navigating the Semantic Web. In Proc. of ISWC, 2002, 469--474. Google ScholarDigital Library
- Rijsbergen, C. Information Retrieval. 1979. Google ScholarDigital Library
- Roth, D. and Yih, W. Integer Linear Programming Inference for Conditional Random Fields. In Proc. of ICML, 2005, 736--743. Google ScholarDigital Library
- Sarawagi, S. and Cohen, W. Semi-markov Conditional Random Fields for Information Extraction. In Proc. of NIPS, 2004.Google Scholar
- Schneider, K. Information Extraction from Calls for Papers with Conditional Random Fields and Layout Features. In Proc. of AICS, 2005, 267--276.Google Scholar
- Sha, F. and Pereira, F. Shallow Parsing with Conditional Random Fields. In Proc. of HLT-NAACL, 2003. Google ScholarDigital Library
- Tang, J., Hong, M., Li, J., and Liang, B. Tree-structured Conditional Random Fields for Semantic Annotation. In Proc. of ISWC, 2006, 640--653. Google ScholarDigital Library
- Yedidia, J., Freeman, W., and Weiss, Y. Generalized Belief Propagation. In Proc. of NIPS, 2000.Google Scholar
- Zhu, J., Nie, Z., Wen, J., Zhang, B., and Ma, W. 2D Conditional Random Fields for Web Information Extraction. In Proc. of ICML, 2005, 1044--1051. Google ScholarDigital Library
- Zhu, J., Nie, Z., Wen, J., Zhang, B., and Ma, W. Simultaneous Record Detection and Attribute Labeling in Web Data Extraction. In Proc. of KDD, 2006, 494--503 Google ScholarDigital Library
Recommendations
Hierarchical hidden conditional random fields for information extraction
LION'05: Proceedings of the 5th international conference on Learning and Intelligent OptimizationHidden Markov Models (HMMs) are very popular generative models for time series data. Recent work, however, has shown that for many tasks Conditional Random Fields (CRFs), a type of discriminative model, perform better than HMMs. Information extraction ...
Table extraction using conditional random fields
SIGIR '03: Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrievalThe ability to find tables and extract information from them is a necessary component of data mining, question answering, and other information retrieval tasks. Documents often contain tables in order to communicate densely packed, multi-dimensional ...
Exploitation de connaissances domaine pour l'interprétation d'images image understanding using domain knowledge
RIAO '04: Coupling approaches, coupling media and coupling languages for information retrievalPour être réellement efficaces, les outils d'indexation d'images doivent être automatiques en terme d'analyse et de description du contenu. Le fossé sémantique existant entre les concepts haut-niveau et des descripteurs bas-niveau (couleur, texture), ...
Comments