Semi-Supervised Neural Machine Translation via Marginal Distribution Estimation
IEEE/ACM Transactions on Audio, Speech, and Language Processing, pp. 1564-1576, 2019.
Neural machine translation (NMT) heavily relies on parallel bilingual corpora for training. Since large-scale, high-quality parallel corpora are usually costly to collect, it is appealing to exploit monolingual corpora to improve NMT. Inspired by the law of total probability, which connects the probability of a given target-side monolingu...More
Full Text (Upload PDF)
PPT (Upload PPT)