Comparison of SMT and NMT trained with large Patent Corpora: Japio at WAT2017
2017-11-01WS 2017Unverified0· sign in to hype
Satoshi Kinoshita, Tadaaki Oshio, Tomoharu Mitsuhashi
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
Japio participates in patent subtasks (JPC-EJ/JE/CJ/KJ) with phrase-based statistical machine translation (SMT) and neural machine translation (NMT) systems which are trained with its own patent corpora in addition to the subtask corpora provided by organizers of WAT2017. In EJ and CJ subtasks, SMT and NMT systems whose sizes of training corpora are about 50 million and 10 million sentence pairs respectively achieved comparable scores for automatic evaluations, but NMT systems were superior to SMT systems for both official and in-house human evaluations.