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...
This paper describes the application of so-called topic models to selectional preference induction. Three models related to Latent Dirichlet Allocation, a proven method for modell...
We describe a cross-lingual method for the induction of selectional preferences for resourcepoor languages, where no accurate monolingual models are available. The method uses bil...
The Internet is increasingly used as a medium for providing medical information. Nevertheless, whether the World Wide Web is favoured over other information sources depends to a l...
Many machine translation (MT) evaluation metrics have been shown to correlate better with human judgment than BLEU. In principle, tuning on these metrics should yield better syste...