For complex tasks such as parse selection, the creation of labelled training sets can be extremely costly. Resource-efficient schemes for creating informative labelled material mu...
The LR parser generators that are bundled with many functional programming language implementations produce code that is untyped, needlessly inefficient, or both. We show that, us...
We present algorithms for higher-order dependency parsing that are "third-order" in the sense that they can evaluate substructures containing three dependencies, and &qu...
With performance above 97% accuracy for newspaper text, part of speech (POS) tagging might be considered a solved problem. Previous studies have shown that allowing the parser to ...
: Graph parsing is known to be computationally expensive. For this reason the construction of special-purpose parsers may be beneficial for particular graph languages. In the domai...