Word Rewarding for Adequate Neural Machine Translation
Word Rewarding for Adequate Neural Machine Translation
复制标题
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Yuto Takebayashi;Chu Chenhui;Yuki Arase;M. Nagata
中科院分区：
文献类型：
--
作者：
Yuto Takebayashi;Chu Chenhui;Yuki Arase;M. Nagata
为了提高神经机器翻译（NMT）的翻译充分性，我们提出了一个奖励模型与目标词预测使用双语词典的启发解码器约束在统计机器翻译的成功。特别是，该模型首先预测一组有希望翻译的目标词;然后提高预测词的概率，使它们有更好的机会被输出。我们的奖励模型与解码器的交互最小，因此它可以很容易地应用到现有的NMT系统的解码器。在资源丰富和资源贫乏的情况下进行的广泛评估表明：（1）使用Oracle预测的BLEU得分提高了10个点以上，（2）使用手动或自动创建的双语词典进行目标词预测的BLEU得分提高了约1.0个点，（3）我们模型的超参数相对容易优化，（4）生成不足的问题可以通过增加过度生成的词来得到缓解。
To improve the translation adequacy in neural machine translation (NMT), we propose a rewarding model with target word prediction using bilingual dictionaries inspired by the success of decoder constraints in statistical machine translation. In particular, the model first predicts a set of target words promising for translation; then boosts the probabilities of the predicted words to give them better chances to be output. Our rewarding model minimally interacts with the decoder so that it can be easily applied to the decoder of an existing NMT system. Extensive evaluation under both resource-rich and resource-poor settings shows that (1) BLEU score improves more than 10 points with oracle prediction, (2) BLEU score improves about 1.0 point with target word prediction using bilingual dictionaries created either manually or automatically, (3) hyper-parameters of our model are relatively easy to optimize, and (4) undergeneration problem can be alleviated in exchange for increasing over-generated words.