Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translation
This work addresses the efficiency-effectiveness gap in machine translation for NLP practitioners, though it is incremental as it builds on existing non-autoregressive models.
The paper tackles the trade-off between speed and translation quality in non-autoregressive neural machine translation by incorporating syntactic and semantic structures, achieving significantly faster speed while maintaining translation quality on WMT14 En-De and WMT16 En-Ro datasets.
The non-autoregressive models have boosted the efficiency of neural machine translation through parallelized decoding at the cost of effectiveness when comparing with the autoregressive counterparts. In this paper, we claim that the syntactic and semantic structures among natural language are critical for non-autoregressive machine translation and can further improve the performance. However, these structures are rarely considered in the existing non-autoregressive models. Inspired by this intuition, we propose to incorporate the explicit syntactic and semantic structures of languages into a non-autoregressive Transformer, for the task of neural machine translation. Moreover, we also consider the intermediate latent alignment within target sentences to better learn the long-term token dependencies. Experimental results on two real-world datasets (i.e., WMT14 En-De and WMT16 En-Ro) show that our model achieves a significantly faster speed, as well as keeps the translation quality when compared with several state-of-the-art non-autoregressive models.