Rethinking Translation Memory Augmented Neural Machine Translation
Hongkun Hao, Guoping Huang, Lemao Liu, Zhirui Zhang, Shuming Shi, Rui Wang · 2023
This paper rethinks translation memory augmented neural machine translation (TMaugmented NMT) from two perspectives, i.e., a probabilistic view of retrieval and the variancebias decomposition principle.The finding demonstrates that TM-augmented NMT is good at the ability of fitting data (i.e., lower bias) but is more sensitive to the fluctuations in the training data (i.e., higher variance), which provides an explanation to a recently reported contradictory phenomenon on the same translation task: TM-augmented NMT substantially advances vanilla NMT under the high-resource scenario whereas it fails under the low-resource scenario.Then we propose a simple yet effective TM-augmented NMT model to promote the variance and address the contradictory phenomenon.Extensive experiments show that the proposed TMaugmented NMT achieves consistent gains over both conventional NMT and existing TM-augmented NMT under two variancepreferable (low-resource and plug-and-play) scenarios as well as the high-resource scenario.