We explore a stacked framework for learning to predict dependency structures for natural language sentences. A typical approach in graph-based dependency parsing has been to assum...
Dual decomposition has been recently proposed as a way of combining complementary models, with a boost in predictive power. However, in cases where lightweight decompositions are ...
Many state-of-the-art statistical parsers for English can be viewed as Probabilistic Context-Free Grammars (PCFGs) acquired from treebanks consisting of phrase-structure trees enri...
Semantic taxonomies such as WordNet provide a rich source of knowledge for natural language processing applications, but are expensive to build, maintain, and extend. Motivated by...