We present a new method that compresses sentences by removing words. In a first stage, it generates candidate compressions by removing branches from the source sentence's dep...
A central problem in grounded language acquisition is learning the correspondences between a rich world state and a stream of text which references that world state. To deal with ...
This paper investigates the class of TreeTuple MCTAG with Shared Nodes, TTMCTAG for short, an extension of Tree Adjoining Grammars that has been proposed for natural language proc...
This paper explores methods to alleviate the effect of lexical sparseness in the classification of verbal arguments. We show how automatically generated selectional preferences ar...
We examine correlations between native speaker judgements on automatically generated German text against automatic evaluation metrics. We look at a number of metrics from the MT a...