Publication View

Named Entity Recognition as a House of Cards: Classifier Stacking (2007)

Abstract
This paper presents a classifier stacking-based approach to the named entity recognition task (NER henceforth). Transformation-based learning (Brill, 1995), Snow (sparse network of winnows (Mu oz et al., 1999)) and a forward-backward algorithm are stacked (the output of one classifier is passed as input to the next classifier), yielding considerable improvement in performance. In addition, in agreement with other studies on the same problem, the enhancement of the feature space (in the form of capitalization information) is shown to be especially beneficial to this task.. The original document contains color images.

Publication details
Download http://handle.dtic.mil/100.2/ADA459582
Contributors JOHNS HOPKINS UNIV BALTIMORE MD CENTER FOR LANGUAGE AND SPEECH PROCESSING (CLSP)
Repository Defense Technical Information Center OAI-PMH Repository (United States)
Keywords LINGUISTICS, NUMERICAL MATHEMATICS, *INFORMATION RETRIEVAL, *NATURAL LANGUAGE, ALGORITHMS, NETWORKS, RECOGNITION, CLASSIFICATION, SAMPLING
Language eng