This paper investigates unsupervised vocabulary and language model self-adaptation (VLA) from just one speech file using the web as a knowledge source and without prior knowledge...
Abstract. This paper presents our recent work on period disambiguation, the kernel problem in sentence boundary identification, with the maximum entropy (Maxent) model. A number o...
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,...
Discriminative learning methods are widely used in natural language processing. These methods work best when their training and test data are drawn from the same distribution. For...
In limited data domains, many effective language modeling techniques construct models with parameters to be estimated on an in-domain development set. However, in some domains, no...