Dynamic Oracle for Neural Machine Translation in Decoding Phase
This work addresses a specific technical problem in NMT for machine translation researchers, but it is incremental as it builds on existing Scheduled Sampling methods.
The paper tackled the discrepancy between training and inference in Neural Machine Translation (NMT) during decoding, which can cause the model to encounter unseen states, by proposing two dynamic oracle-based methods to improve Scheduled Sampling, resulting in improved translation quality over standard NMT systems.
The past several years have witnessed the rapid progress of end-to-end Neural Machine Translation (NMT). However, there exists discrepancy between training and inference in NMT when decoding, which may lead to serious problems since the model might be in a part of the state space it has never seen during training. To address the issue, Scheduled Sampling has been proposed. However, there are certain limitations in Scheduled Sampling and we propose two dynamic oracle-based methods to improve it. We manage to mitigate the discrepancy by changing the training process towards a less guided scheme and meanwhile aggregating the oracle's demonstrations. Experimental results show that the proposed approaches improve translation quality over standard NMT system.