Common wisdom has it that tile bias of stochastic grammars in favor of shorter deriwttions of a sentence is hamfful and should be redressed. We show that the common wisdom is wron...
The goal of text categorization is to classify documents into a certain number of pre-defined categories. The previous works in this area have used a large number of labeled train...
Sharing portions of grammars across languages greatly reduces the costs of multilingual grammar engineering. Related languages share a much wider range of linguistic information t...
This research looks at the effects of word order and segmentation on translation retrieval performance for an experimental Japanese-English translation memory system. We implement...
The Computing Research laboratory (CRL) is developing a machine translation toolkit that allows rapid deployment of translation capabilities. This toolkit has been used to develop...
The paper illustrates a linguistic knowledge acquisition model making use of data types, innite memory, and an inferential mechanism for inducing new information from known data. ...
Paolo Allegrini, Simonetta Montemagni, Vito Pirrel...