Paper: Improving NLP through Marginalization of Hidden Syntactic Structure

ACL ID D12-1074
Title Improving NLP through Marginalization of Hidden Syntactic Structure
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2012
Authors

Many NLP tasks make predictions that are in- herently coupled to syntactic relations, but for many languages the resources required to pro- vide such syntactic annotations are unavail- able. For others it is unclear exactly how much of the syntactic annotations can be ef- fectively leveraged with current models, and what structures in the syntactic trees are most relevant to the current task. We propose a novel method which avoids the need for any syntactically annotated data when predicting a related NLP task. Our method couples latent syntactic representa- tions, constrained to form valid dependency graphs or constituency parses, with the predic- tion task via specialized factors in a Markov random field. At both training and test time we marginalize over this hidden structure, learn- in...