神经机器翻译WMT14英法基准系统 WMT14 English-French Baseline

 

最近（2017年以来）的WMT14 English-French Baseline记录

 

1. GNMT

   https://arxiv.org/pdf/1609.08144.pdf

   语料处理：a shared source and target vocabulary of 32K wordpieces

     For the wordpiece models, we train 3 different models with vocabulary sizes of 8K, 16K, and 32K. Table 4 summarizes our results on the WMT En→Fr dataset. In this table, we also compare against other strong baselines without model ensembling. As can be seen from the table, “WPM-32K”, a wordpiece model with a shared source and target vocabulary of 32K wordpieces, performs well on this dataset and achieves the best quality as well as the fastest inference speed.

    On WMT En→Fr, the training set contains 36M sentence pairs. In both cases, we use newstest2014 as the test sets to compare against previous work. The combination of newstest2012 and newstest2013 is used as the development