Augmenting Statistical Machine Translation with Subword Translation of Out-of-Vocabulary Words
arXiv: Computation and Language, Volume abs/1808.05700, 2018.
Most statistical machine translation systems cannot translate words that are unseen in the training data. However, humans can translate many classes of out-of-vocabulary (OOV) words (e.g., novel morphological variants, misspellings, and compounds) without context by using orthographic clues. Following this observation, we describe and eva...More
Full Text (Upload PDF)
PPT (Upload PPT)