A Tree-based Decoder for Neural Machine Translation
This addresses the challenge of selecting effective structural representations for NMT, showing incremental improvements over existing methods.
The paper tackled the problem of improving Neural Machine Translation by incorporating syntactic information, and found that using balanced binary trees without linguistic knowledge outperformed standard seq2seq models by up to 2.1 BLEU points and other syntax-based methods by up to 0.7 BLEU.
Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguistically-inspired tree structures, like constituency and dependency parse trees. This is often done via a standard RNN decoder that operates on a linearized target tree structure. However, it is an open question of what specific linguistic formalism, if any, is the best structural representation for NMT. In this paper, we (1) propose an NMT model that can naturally generate the topology of an arbitrary tree structure on the target side, and (2) experiment with various target tree structures. Our experiments show the surprising result that our model delivers the best improvements with balanced binary trees constructed without any linguistic knowledge; this model outperforms standard seq2seq models by up to 2.1 BLEU points, and other methods for incorporating target-side syntax by up to 0.7 BLEU.