Shallow Parsing as Part-of-Speech Tagging
暂无分享,去创建一个
Treating shallow parsing as part-of-speech tagging yields results comparable with other, more elaborate approaches. Using the CoNLL 2000 training and testing material, our best model had an accuracy of 94.88%, with an overall FB1 score of 91.94%. The individual FB1 scores for NPs were 92.19%, VPs 92.70% and PPs 96.69%.
[1] Mitchell P. Marcus,et al. Text Chunking using Transformation-Based Learning , 1995, VLC@ACL.
[2] Claire Cardie,et al. Error-Driven Pruning of Treebank Grammars for Base Noun Phrase Identification , 1998, ACL.
[3] Walter Daelemans,et al. Cascaded Grammatical Relation Assignment , 1999, EMNLP.
[4] Christopher D. Manning,et al. Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger , 2000, EMNLP.