Incorporating translation quality estimation into Chinese-Korean neural machine translation

Incorporating translation quality estimation into Chinese-Korean neural machine translation Feiyu Li, Yahui Zhao∗, Feiyang Yang, Rongyi Cui Department of Computer Science and Technology, Yanbian University, Yianbian, China {2019010431,yhzhao,2018010454,cuirongyi}@ybu.edu.cn Abstract Exposure bias and poor translation diversity are two common problems in neural machine trans- lation (NMT), which are caused by the general of the teacher forcing strategy for training in the NMT models. Moreover, the NMT models usually require the large-scale and high-quality parallel corpus. However, Korean is a low resource language, and there is no large-scale parallel corpus between Chinese and Korean, which is a challenging for the researchers. Therefore, we propose a method which is to incorporate translation quality estimation into the translation process and adopt reinforcement learning. The evaluation mechanism is used to guide the training of the model, so that the prediction cannot converge completely to the ground truth word. When the model predicts a sequence different from the ground truth word, the evaluation mechanism can give an appropriate evaluation and reward to the model. In addition, we alleviated the lack of Korean corpus resources by adding training data. In our experiment, we introduce a monolingual corpus of a certain scale to construct pseudo-parallel data. At the same time, we also preprocessed the Korean corpus with different granularities to overcome the data sparsity. Experimental results show that our work is superior to the baselines in Chinese-Korean and Korean-Chinese translation tasks, which fully certificates the effectiveness of our method. 1 Introduction With the rapid development of deep learning, neural machine translation(NMT) has attracted much attention in recent years. This is because it has superior performance and does not require much manual intervention(Bahdanau D, 2015)(Junczys-Dowmunt M, 2016). Korean is the official language of the Korean ethnic group in China, and is also used in the Korean Peninsula, the United States, the Russian Far East and other areas where Koreans congregate. Transnational and transregional is a key feature of Korean. As the Korean ethnic group is one of the 24 ethnic minorities in China that have their own language(Yongshou, 2020), the research on Chinese-Korean neural machine translation plays an important role in promoting the language work of ethnic minorities and strengthening the communication and unity of ethnic groups. At present, most NMT models adopt the teacher forcing strategy in training(Williams RJ, 1989). Teacher forcing is to minimize the difference between the source sentence and the reference and force the predicted translation to be infinitely close to the reference. First of all, as there is usually no reference for sentence prediction, exposure bias will be brought, which may affect the performance and robustness of the model (Ranzato M, 2016). Secondly, as there are a large number of synonyms and similar expressions in the language, the translation model cannot always generate the ground truth word even with teacher forcing in training. Using this strategy will greatly curb the diversity of translation and make many reasonable translations in an unreachable state(Zhang W, 2019). In addition, domestic research on Chinese-Korean machine translation started late, …

Content truncated to 500 words