ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Weakly supervised parsing with rules

C. Cerisara, A. Lorenzo, P. Kral

This work proposes a new research direction to address the lack of structures in traditional n-gram models. It is based on a weakly supervised dependency parser that can model speech syntax without relying on any annotated training corpus. Labeled data is replaced by a few hand-crafted rules that encode basic syntactic knowledge. Bayesian inference then samples the rules, disambiguating and combining them to create complex tree structures that maximize a discriminative model's posterior on a target unlabeled corpus. This posterior encodes sparse selectional preferences between a head word and its dependents. The model is evaluated on English and Czech newspaper texts, and is then validated on French broadcast news transcriptions.


doi: 10.21437/Interspeech.2013-517

Cite as: Cerisara, C., Lorenzo, A., Kral, P. (2013) Weakly supervised parsing with rules. Proc. Interspeech 2013, 2192-2196, doi: 10.21437/Interspeech.2013-517

@inproceedings{cerisara13_interspeech,
  author={C. Cerisara and A. Lorenzo and P. Kral},
  title={{Weakly supervised parsing with rules}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={2192--2196},
  doi={10.21437/Interspeech.2013-517}
}