In this work, we attempt to tackle domain-transfer problem by combining old-domain labeled examples with new-domain unlabeled ones. The basic idea is to use old-domain-trained cla...
This paper presents four novel techniques for open-vocabulary spoken document retrieval: a method to detect slots that possibly contain a query feature; a method to estimate occurr...
There is considerable interest in interdisciplinary combinations of automatic speech recognition (ASR), machine learning, natural language processing, text classification and info...
Mark Dredze, Aren Jansen, Glen Coppersmith, Ken Wa...
The goal of DARPA's Machine Reading (MR) program is nothing less than making the world's natural language corpora available for formal processing. Most text processing r...
Stephanie Strassel, Dan Adams, Henry Goldberg, Jon...
One of the grand challenges of AI is to build systems that learn by reading. The ideal system would construct a rich knowledge base capable of automated reasoning. We have built a...