摘要
对于句子级别的神经机器翻译,由于不考虑句子所处的上下文信息,往往存在句子语义表示不完整的问题。该文通过依存句法分析,对篇章中的每句话提取有效信息,再将提取出的信息,补全到源端句子中,使得句子的语义表示更加完整。该文在汉语-英语语言对上进行了实验,并针对篇章语料稀少的问题,提出了在大规模句子级别的平行语料上的训练方法。相比于基准系统,该文提出的方法获得了1.47个BLEU值的提高。实验表明,基于补全信息的篇章级神经机器翻译,可以有效地解决句子级别神经机器翻译语义表示不完整的问题。
For sentence-level neural machine translation, the problem of incomplete semantic representation is noticeable since the context information of the current sentence is not considered. We extract effective information from each sentence in a document by dependency parsing, and then complement the extracted information into the source sentences, making the semantic representation of the sentences more complete. We conduct experiments on Chinese-English language pair, and propose a training method on large-scale parallel language pairs for the scarcity of document-level parallel corpus. Compared with the baseline model, our approach improves 1.47 BLEU significantly. Experiments show that the document-level neural machine translation based on context recovery can effectively solve the problem of incomplete semantic representation of sentence-level neural machine translation.
作者
张培
张旭
熊德意
ZHANG Pei;ZHANG Xu;XIONG Deyi(School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China;AI Interactive Center,Sogou,Beijing 100089,China)
出处
《中文信息学报》
CSCD
北大核心
2020年第7期60-67,共8页
Journal of Chinese Information Processing
基金
国家自然科学基金(61861130364)
关键词
神经机器翻译
篇章
补全
neural machine translation
document
context recovery
