基于单语优先级采样自训练神经机器翻译的研究OA北大核心CSTPCD

To enhance the performance of neural machine translation(NMT)and ameliorate the detrimental impact of high uncertainty in monolingual data during the self-training process,a self-training NMT model based on priority sam-pling was proposed.Initially,syntactic dependency trees were constructed and the importance of monolingual tokeniza-tion was assessed using grammar dependency analysis.Subsequently,a monolingual lexicon was built,and priority was defined based on the importance of monolingual tokenization and uncertainty.Finally,monolingual priorities were com-puted,and sampling was carried out based on these priorities,consequently generating a synthetic parallel dataset for training the student NMT model.Experimental results on a large-scale subset of the WMT English to German dataset demonstrate that the proposed model effectively enhances NMT translation performance and mitigates the impact of high uncertainty on the model.