论文信息 - Classifying the Hungarian Web

Classifying the Hungarian Web

In this paper we present some lessons learned from building vizsla, the keyword search and topic classification system used on the largest Hungarian portal, [origo.hu]. Based on a simple statistical language, model, and the large-scale supporting evidence from vizsla, we argue that in topic classification only positive evidence matters.

[1] Djoerd Hiemstra,et al. Twenty-One at TREC7: Ad-hoc and Cross-Language Track , 1998, TREC.

[2] W. Highleyman. Linear Decision Functions, with Application to Pattern Recognition , 1962, Proceedings of the IRE.

[3] Stephen E. Robertson,et al. On relevance weights with little relevance information , 1997, SIGIR '97.

[4] Shigeo Abe DrEng. Pattern Classification , 2001, Springer London.

[5] John Makhoul,et al. Rough'n'Ready: a meeting recorder and browser , 1999, CSUR.

[6] András Kornai,et al. Linear Discriminant Text Classification in High Dimension , 2001, HIS.

[7] Richard M. Schwartz,et al. A hidden Markov model information retrieval system , 1999, SIGIR '99.

[8] John D. Lafferty,et al. A study of smoothing methods for language models applied to Ad Hoc information retrieval , 2001, SIGIR '01.

[9] David G. Stork,et al. Pattern Classification , 1973 .