Foreign Language Department, Henan University of Chinese Medicine, Zhengzhou 450000, Henan, China.
Comput Intell Neurosci. 2022 Jun 11;2022:1662311. doi: 10.1155/2022/1662311. eCollection 2022.
In order to solve the problem of tense consistency in Chinese-English neural machine translation (NMT) system, a Chinese verb tense annotation model is proposed. Firstly, a neural network is used to build a Chinese tense annotation model. During the translation process, the source tense is passed to the target side through the alignment matrix of the traditional Attention mechanism. The probability of the candidate words inconsistent with the corresponding tense of source words in the candidate translation word set is also reduced. Then, the Chinese-English temporal annotation algorithm is integrated into the MT model, so as to build a Chinese-English translation system with temporal processing function. The essence of the system is that, in the process of translation, Chinese-English temporal annotation algorithm is used to obtain temporal information from Chinese sentences and transfer it to the corresponding English sentences, so as to realize the temporal processing of English sentences and obtain the English sentences corresponding to the tenses of the original Chinese sentences. The experimental results show that the Chinese tense annotation model of bidirectional long short-term memory (LSTM) is more accurate for the prediction of Chinese verb tense, so the improvement effect of NMT model is also the most obvious, especially on the NIST06 test set, where the BLEU value is increased by 1.07%. As the mainstream translation model, the transformer model contains multihead Attention mechanism, which can pay attention to some temporal information and has a certain processing ability for temporal translation. It solves the tense problems encountered in the process of MT and improves the credibility of Chinese-English machine translation (MT).
为了解决汉英神经机器翻译（NMT）系统中时态一致性的问题，提出了一种汉语动词时态标注模型。首先，使用神经网络构建汉语时态标注模型。在翻译过程中，通过传统注意力机制的对齐矩阵将源时态传递到目标端，同时降低候选翻译词集中与源词对应时态不一致的候选词的概率。然后，将汉英时态标注算法集成到 MT 模型中，构建具有时态处理功能的汉英翻译系统。系统的本质是在翻译过程中，使用汉英时态标注算法从汉语句子中获取时态信息并将其转换为相应的英语句子，从而实现英语句子的时态处理，获得与汉语句子时态对应的英语句子。实验结果表明，双向长短期记忆（LSTM）的汉语时态标注模型对汉语动词时态的预测更加准确，因此对 NMT 模型的改进效果也最为明显，尤其是在 NIST06 测试集上，BLEU 值提高了 1.07%。作为主流的翻译模型，Transformer 模型包含多头注意力机制，可以关注一些时态信息，对时态翻译具有一定的处理能力。它解决了 MT 过程中遇到的时态问题，提高了汉英机器翻译（MT）的可信度。
