作者: Ting-hui Kao , Jason S. Chang , Mei-hua Chen , Chung-chi Huang , Hung-ting Hsieh
DOI:
关键词:
摘要: We introduce a method for learning to predict the following grammar and text of ongoing translation given source text. In our approach, predictions are offered aimed at reducing users' burden on lexical choices, improving productivity. The involves syntactic phraseology equivalents. At run-time, its prefix sliced into ngrams generate subsequent predictions. present prototype writing assistant, TransAhead, that applies where computer-assisted language meet. preliminary results show has great potentials in CAT CALL (significant boost quality is observed).