Time-Aware Ancient Chinese Text Translation and Inference

Abstract

In this paper, we aim to address the challenges surrounding the translation of ancient Chinese text: (1) The linguistic gap due to the difference in eras results in translations that are poor in quality, and (2) most translations are missing the contextual information that is often very crucial to understanding the text. To this end, we improve upon past translation techniques by proposing the following: We reframe the task as a multi-label prediction task where the model predicts both the translation and its particular era. We observe that this helps to bridge the linguistic gap as chronological context is also used as auxiliary information. We validate our framework on a parallel corpus annotated with chronology information and show experimentally its efficacy in producing quality translation outputs. We release both the code and the data 1 for future research.

Comparison and analysis of two methods for improving the accuracy of OpenNMT in literary and vernacular Chinese translation

“…Wei developed a Classical Chinese to Vernacular Chinese translation model based on external knowledge collaboration, which effectively improves translation performance [2]. Chang designed a multi-label prediction task, utilizing temporal information from the ancient text as translation assistance and enhancing translation quality based on contextual time order [3]. These approaches have significantly contributed to machine translation between Literary and Vernacular Chinese.…”