Weakly Supervised Parsing with Rules
Interspeech 2013 (2013)
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
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.
Authors of the publication