Data-driven learning based on shift reduce parsing algorithms has emerged dependency parsing and shown excellent performance to many Treebanks. In this paper, we investigate the e...
Recent syntactic extensions of statistical translation models work with a synchronous context-free or tree-substitution grammar extracted from an automatically parsed parallel cor...
We describe our experiments using the DeSR parser in the multilingual and domain adaptation tracks of the CoNLL 2007 shared task. DeSR implements an incremental deterministic Shif...
Giuseppe Attardi, Felice dell'Orletta, Maria Simi,...
Most state-of-the-art wide-coverage parsers are trained on newspaper text and suffer a loss of accuracy in other domains, making parser adaptation a pressing issue. In this paper ...
Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...