Paper: Constituent Parsing By Classification

ACL ID W05-1515
Title Constituent Parsing By Classification
Venue Workshop On Parsing Technology
Year 2005

Ordinary classification techniques can drive a conceptually simple constituent parser that achieves near state-of-the-art accuracy on standard test sets. Here we present such a parser, which avoids some of the limitations of other discriminative parsers. In particular, it does not place any restrictions upon which types of fea- tures are allowed. We also present sev- eral innovations for faster training of dis- criminative parsers: we show how train- ing can be parallelized, how examples can be generated prior to training with- out a working parser, and how indepen- dently trained sub-classifiers that have never done any parsing can be effectively combined into a working parser. Finally, we propose a new figure-of-merit for best- first parsing with confidence-rated infer- ences.

  author    = {Turian, Joseph  and  Melamed, I. Dan},
  title     = {Constituent Parsing by Classification},
  booktitle = {Proceedings of the Ninth International Workshop on Parsing Technology},
  month     = {October},
  year      = {2005},
  address   = {Vancouver, British Columbia},
  publisher = {Association for Computational Linguistics},
  pages     = {141--151},
  url       = {}