no code implementations • WS 2017 • Zi Long, Ryuichiro Kimura, Takehito Utsuro, Tomoharu Mitsuhashi, Mikio Yamamoto
Long et al.(2017) proposed to select phrases that contain out-of-vocabulary words using the statistical approach of branching entropy.
no code implementations • WS 2017 • Satoshi Kinoshita, Tadaaki Oshio, Tomoharu Mitsuhashi
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.
no code implementations • MTSummit 2017 • Zi Long, Ryuichiro Kimura, Takehito Utsuro, Tomoharu Mitsuhashi, Mikio Yamamoto
Neural machine translation (NMT), a new approach to machine translation, has achieved promising results comparable to those of traditional approaches such as statistical machine translation (SMT).
no code implementations • WS 2016 • Zi Long, Takehito Utsuro, Tomoharu Mitsuhashi, Mikio Yamamoto
We train an NMT system on bilingual data wherein technical terms are replaced with technical term tokens; this allows it to translate most of the source sentences except technical terms.
no code implementations • WS 2016 • Satoshi Kinoshita, Tadaaki Oshio, Tomoharu Mitsuhashi, Terumasa Ehara
In scientific paper subtask, our translations are given lower scores than most translations that are produced by translation engines trained with the in-domain corpora.