Transformation-Based Learning in the Fast Lane Export

@misc{citeulike:176904, abstract = {Transformation-based learning has been successfully employed to solve many natural language processing problems. It achieves state-of-the-art performance on many natural language processing tasks and does not overtrain easily. However, it does have a serious drawback: the training time is often intorelably long, especially on the large corpora which are often used in NLP. In this paper, we present a novel and realistic method for speeding up the training time of a transformation-based learner without sacrificing performance. The paper compares and contrasts the training time needed and performance achieved by our modified learner with two other systems: a standard transformation-based learner, and the ICA system \cite{hepple00:tbl}. The results of these experiments show that our system is able to achieve a significant improvement in training time while still achieving the same performance as a standard transformation-based learner. This is a valuable contribution to systems and algorithms which utilize transformation-based learning at any part of the execution.}, archivePrefix = {arXiv}, author = {Ngai, Grace and Florian, Radu}, citeulike-article-id = {176904}, citeulike-linkout-0 = {http://arxiv.org/abs/cs.CL/0107020}, citeulike-linkout-1 = {http://arxiv.org/pdf/cs.CL/0107020}, day = {17}, eprint = {cs.CL/0107020}, keywords = {tbedl}, month = {July}, posted-at = {2005-05-03 02:17:14}, priority = {2}, title = {Transformation-Based Learning in the Fast Lane}, url = {http://arxiv.org/abs/cs.CL/0107020}, year = {2001} }

TY - ELEC ID - citeulike:176904 L3 - citeulike-article-id:176904 N2 - Transformation-based learning has been successfully employed to solve many natural language processing problems. It achieves state-of-the-art performance on many natural language processing tasks and does not overtrain easily. However, it does have a serious drawback: the training time is often intorelably long, especially on the large corpora which are often used in NLP. In this paper, we present a novel and realistic method for speeding up the training time of a transformation-based learner without sacrificing performance. The paper compares and contrasts the training time needed and performance achieved by our modified learner with two other systems: a standard transformation-based learner, and the ICA system \cite{hepple00:tbl}. The results of these experiments show that our system is able to achieve a significant improvement in training time while still achieving the same performance as a standard transformation-based learner. This is a valuable contribution to systems and algorithms which utilize transformation-based learning at any part of the execution. TI - Transformation-Based Learning in the Fast Lane KW - tbedl AU - Ngai, Grace AU - Florian, Radu PY - 2001/07/17/ UR - http://arxiv.org/abs/cs.CL/0107020 ER -