Multi-Source Syntactic Neural Machine Translation

Autor:	Currey, Anna, Heafield, Kenneth
Rok vydání:	2018
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses. This is achieved by employing separate encoders for the sequential and parsed versions of the same source sentence; the resulting representations are then combined using a hierarchical attention mechanism. The proposed model improves over both seq2seq and parsed baselines by over 1 BLEU on the WMT17 English-German task. Further analysis shows that our multi-source syntactic model is able to translate successfully without any parsed input, unlike standard parsed methods. In addition, performance does not deteriorate as much on long sentences as for the baselines. Comment: EMNLP 2018
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1808.10267 Zobrazit plný text záznamu View this record from Arxiv