In this paper, we present a Support Vector Machine (SVM) based ensemble approach to combat the extractive multi-document summarization problem. Although SVM can have a good generalization ability, it may experience a performance degradation through wrong classifications. We use a committee of several SVMs, i.e. Cross-Validation Committees (CVC), to form an ensemble of classifiers where the strategy is to improve the performance by correcting errors of one classifier using the accurate output of others. The practicality and effectiveness of this technique is demonstrated using the experimental results.

@inproceedings{chali-hasan-joty-cai-09, abstract = {In this paper, we present a Support Vector Machine (SVM) based ensemble approach to combat the extractive multi-document summarization problem. Although SVM can have a good generalization ability, it may experience a performance degradation through wrong classifications. We use a committee of several SVMs, i.e. Cross-Validation Committees (CVC), to form an ensemble of classifiers where the strategy is to improve the performance by correcting errors of one classifier using the accurate output of others. The practicality and effectiveness of this technique is demonstrated using the experimental results.}, acmid = {1560492}, address = {Berlin, Heidelberg}, author = {Chali*, Yllias and Hasan*, Sadid and Joty*, Shafiq}, booktitle = {Proceedings of the 22Nd Canadian Conference on Artificial Intelligence: Advances in Artificial Intelligence}, doi = {10.1007/978-3-642-01818-3_23}, isbn = {978-3-642-01817-6}, location = {Kelowna, Canada}, numpages = {4}, pages = {199--202}, publisher = {Springer-Verlag}, series = {Canadian AI '09}, title = {A SVM-Based Ensemble Approach to Multi-Document Summarization}, url = {http://dx.doi.org/10.1007/978-3-642-01818-3_23}, year = {2009} }