Understanding Neural Machine Translation by Simplification: The Case of Encoder-free Models
Gongbo Tang, Rico Sennrich, Joakim Nivre · 2019
In this paper, we try to understand neural machine translation (NMT) via simplifying NMT architectures and training encoder-free NMT models.In an encoderfree model, the sums of word embeddings and positional embeddings represent the source.The decoder is a standard Transformer or recurrent neural network that directly attends to embeddings via attention mechanisms.Experimental results show (1) that the attention mechanism in encoder-free models acts as a strong feature extractor, (2) that the word embeddings in encoder-free models are competitive to those in conventional models, (3) that non-contextualized source representations lead to a big performance drop, and (4) that encoder-free models have different effects on alignment quality for German→English and Chinese→English.