Multi-agent Learning for Neural Machine Translation
This work addresses translation quality in neural machine translation, but it is incremental as it builds on existing multi-agent concepts like dual learning.
The paper tackles the problem of improving neural machine translation by extending single-agent training to a multi-agent framework where diverse agents interactively learn from each other. The approach achieves absolute improvements over strong baselines and competitive performance across multiple translation tasks, including NIST Chinese-English and WMT 2014 English-German.
Conventional Neural Machine Translation (NMT) models benefit from the training with an additional agent, e.g., dual learning, and bidirectional decoding with one agent decoding from left to right and the other decoding in the opposite direction. In this paper, we extend the training framework to the multi-agent scenario by introducing diverse agents in an interactive updating process. At training time, each agent learns advanced knowledge from others, and they work together to improve translation quality. Experimental results on NIST Chinese-English, IWSLT 2014 German-English, WMT 2014 English-German and large-scale Chinese-English translation tasks indicate that our approach achieves absolute improvements over the strong baseline systems and shows competitive performance on all tasks.