Paper: Why Nitpicking Works: Evidence For Occam's Razor In Error Correctors

ACL ID C04-1058
Title Why Nitpicking Works: Evidence For Occam's Razor In Error Correctors
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2004
Authors
  • Dekai Wu (University of Science and Technology, Clear Water Bay Hong Kong; Hong Kong Polytechnic University, Hung Hom Hong Kong)
  • Grace Ngai (Hong Kong Polytechnic University, Hung Hom Hong Kong)
  • Marine Carpuat (University of Science and Technology, Clear Water Bay Hong Kong)

Empirical experience and observations have shown us when powerful and highly tunable classifiers such as maximum en- tropy classifiers, boosting and SVMs are applied to language processing tasks, it is possible to achieve high accuracies, but eventually their performances all tend to plateau out at around the same point. To further improve performance, various error correction mechanisms have been developed, but in practice, most of them cannot be relied on to predictably improve per- formance on unseen data; indeed, depending upon the test set, they are as likely to degrade accuracy as to improve it. This problem is especially severe if the base classifier has already been finely tuned. In recent work, we introduced N-fold Templated Piped Cor- rection, or NTPC (“nitpick”), an intrigui...