Semisupervised Learning for Machine Translation
Nicola Ueffing, Gholamreza Haffari, Anoop Sarkar · The MIT Press eBooks · 2008
This chapter proposes algorithms for semisupervised learning. It translates sentences from the source language and then uses them to retrain the statistical machine translation (SMT) system in the hopes of getting a better translation system. It presents detailed experimental evaluations using French-English and Chinese-English data. The French-English translation task used bilingual data from the Europarl corpus, and monolingual data from the same domain as the test set which is drawn from the Canadian Hansard corpus. The Chinese-English task used bilingual data from the NIST large-data track and monolingual data from the Chinese Gigaword corpus.