Coarse-To-Fine Learning for Neural Machine Translation.
Lecture Notes in Artificial Intelligence(2018)
摘要
In this paper, we address the problem of learning better word representations for neural machine translation (NMT). We propose a novel approach to NMT model training based on coarse-to-fine learning paradigm, which is able to infer better NMT model parameters for a wide range of less-frequent words in the vocabulary. To this end, our proposed method first groups source and target words into a set of hierarchical clusters, then a sequence of NMT models are learned based on it with growing cluster granularity. Each subsequent model inherits model parameters from its previous one and refines them with finer-grained word-cluster mapping. Experimental results on public data sets demonstrate that our proposed method significantly outperforms baseline attention-based NMT model on Chinese-English and English-French translation tasks.
更多查看译文
关键词
Neural machine translation,Coarse-to-fine learning,Hierarchical cluster
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络