PCFG parsing with CRF tagging for head recognition

Abstract

This paper presents our work for participation in the 2009 CIPS-Parseval shared task on Chinese syntactic tree parsing, for which we adopt a general PCFG parsing procedure with a conditional random fields (CRF) tagger for head constituent recognition. Our experiments show that an acceptable tagging result is obtained on the basis of a standard PCFG parsing output and a further evaluation on other parsing result also illustrates its effectiveness.

4 Figures and Tables

Cite this paper

@inproceedings{Song2009PCFGPW, title={PCFG parsing with CRF tagging for head recognition}, author={Yan Song}, year={2009} }