This paper shows that the accuracy of learned text classifiers can be improved by augmenting a small number of labeled training documents with a large pool of unlabeled documents. ...
Kamal Nigam, Andrew McCallum, Sebastian Thrun, Tom...
We present an algorithm for pronounanaphora (in English) that uses Expectation Maximization (EM) to learn virtually all of its parameters in an unsupervised fashion. While EM freq...
Incremental processing is relevant for language modeling, speech recognition and language generation. In this paper we devise a dynamic version of Tree Adjoining Grammar (DVTAG) th...
This paper addresses the automatic classification of semantic relations in noun phrases based on cross-linguistic evidence from a set of five Romance languages. A set of novel s...
Finite-state Transducers (FST) can be very efficient to implement inter-dialectal transliteration. We illustrate this on the Hindi and Urdu language pair. FSTs can also be used fo...
M. G. Abbas Malik, Christian Boitet, Pushpak Bhatt...