Long-span features, such as syntax, can improve language models for tasks such as speech recognition and machine translation. However, these language models can be difficult to u...
We investigate the use of Fisher's exact significance test for pruning the translation table of a hierarchical phrase-based statistical machine translation system. In additio...
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework....
This paper presents the second participation of the University of Ottawa group in the Cross-Language Speech Retrieval (CL-SR) task at CLEF 2006. We present the results of the submi...
To understand the subjective documents, for example, public comments on the government’s proposed regulation, opinion identification and classification is required. Rather than ...
Namhee Kwon, Liang Zhou, Eduard H. Hovy, Stuart W....