We investigate the factors which determine constituent order in German clauses and propose an algorithm which performs the task in two steps: First, the best candidate for the ini...
The third PASCAL Recognizing Textual Entailment Challenge (RTE-3) contained an optional task that extended the main entailment task by requiring a system to make three-way entailm...
There is a widely held belief in the natural language and computational linguistics communities that Semantic Role Labeling (SRL) is a significant step toward improving important ...
Mona T. Diab, Alessandro Moschitti, Daniele Pighin
The availability of databases of images labeled with keywords is necessary for developing and evaluating image annotation models. Dataset collection is however a costly and time c...
Previous studies of data-driven dependency parsing have shown that the distribution of parsing errors are correlated with theoretical properties of the models used for learning an...
We present a general framework to incorporate prior knowledge such as heuristics or linguistic features in statistical generative word alignment models. Prior knowledge plays a ro...
We identify four types of errors that unsupervised induction systems make and study each one in turn. Our contributions include (1) using a meta-model to analyze the incorrect bia...