Combining Information Extraction Systems Using Voting and Stacked Generalization Export

@article{citeulike:5430496, abstract = {This article investigates the effectiveness of voting and stacked generalization -also known as stacking- in the context of information extraction (IE). A new stacking framework is proposed that accommodates well-known approaches for IE. The key idea is to perform cross-validation on the base-level data set, which consists of text documents annotated with relevant information, in order to create a meta-level data set that consists of feature vectors. A classifier is then trained using the new vectors. Therefore, base-level IE systems are combined with a common classifier at the meta-level. Various voting schemes are presented for comparing against stacking in various IE domains. Well known IE systems are employed at the base-level, together with a variety of classifiers at the meta-level. Results show that both voting and stacking work better when relying on probabilistic estimates by the base-level systems. Voting proved to be effective in most domains in the experiments. Stacking, on the other hand, proved to be consistently effective over all domains, doing comparably or better than voting and always better than the best base-level systems. Particular emphasis is also given to explaining the results obtained by voting and stacking at the meta-level, with respect to the varying degree of similarity in the output of the base-level systems.}, author = {Sigletos, Georgios and Paliouras, Georgios and Spyropoulos, Constantine D. and Hatzopoulos, Michalis}, citeulike-article-id = {5430496}, citeulike-linkout-0 = {http://www.jmlr.org/papers/volume6/sigletos05a/sigletos05a.pdf}, journal = {Journal of Machine Learning Research}, keywords = {application, ensemble, information\_extraction, stacking}, month = {November}, pages = {1751--1782}, posted-at = {2009-08-13 06:03:07}, priority = {1}, title = {Combining Information Extraction Systems Using Voting and Stacked Generalization}, url = {http://www.jmlr.org/papers/volume6/sigletos05a/sigletos05a.pdf}, volume = {6}, year = {2005} }

TY - JOUR ID - citeulike:5430496 L3 - citeulike-article-id:5430496 N2 - This article investigates the effectiveness of voting and stacked generalization -also known as stacking- in the context of information extraction (IE). A new stacking framework is proposed that accommodates well-known approaches for IE. The key idea is to perform cross-validation on the base-level data set, which consists of text documents annotated with relevant information, in order to create a meta-level data set that consists of feature vectors. A classifier is then trained using the new vectors. Therefore, base-level IE systems are combined with a common classifier at the meta-level. Various voting schemes are presented for comparing against stacking in various IE domains. Well known IE systems are employed at the base-level, together with a variety of classifiers at the meta-level. Results show that both voting and stacking work better when relying on probabilistic estimates by the base-level systems. Voting proved to be effective in most domains in the experiments. Stacking, on the other hand, proved to be consistently effective over all domains, doing comparably or better than voting and always better than the best base-level systems. Particular emphasis is also given to explaining the results obtained by voting and stacking at the meta-level, with respect to the varying degree of similarity in the output of the base-level systems. JF - Journal of Machine Learning Research EP - 1782 TI - Combining Information Extraction Systems Using Voting and Stacked Generalization VL - 6 SP - 1751 KW - application KW - ensemble KW - information_extraction KW - stacking AU - Sigletos, Georgios AU - Paliouras, Georgios AU - Spyropoulos, Constantine AU - Hatzopoulos, Michalis PY - 2005/11// UR - http://www.jmlr.org/papers/volume6/sigletos05a/sigletos05a.pdf ER -