Weighted finite-state transducers have been used successfully in a variety of natural language processing applications, including speech recognition, speech synthesis, and machine ...
We study a number of natural language decipherment problems using unsupervised learning. These include letter substitution ciphers, character code conversion, phonetic deciphermen...
Kevin Knight, Anish Nair, Nishit Rathod, Kenji Yam...
For many years, statistical machine translation relied on generative models to provide bilingual word alignments. In 2005, several independent efforts showed that discriminative m...
Most state-of-the-art evaluation measures for machine translation assign high costs to movements of word blocks. In many cases though such movements still result in correct or alm...
Following the recent adoption by the machine translation community of automatic evaluation using the BLEU/NIST scoring process, we conduct an in-depth study of a similar idea for ...