State of the Art of Research on Information Processing of Pre-Qin Chinese Corpus

State of the Art of research on Information Processing of Pre-Qin Chinese corpus ^[1]∗

—Case Studies with information processing of Mencius and its Annotations and Commentaries

[Abstract] In today’s information age, making use of Pre-Qin documents And exploring automatic processing and use of Pre-Qin Chinese corpus, is very important. — Case Studies with information processing of Mencius and its Annotation Documents, Using Mencius and its annotations and commentaries as case studies, this article summarizes the state of the art of information processing with Pre-Qin documents, covering topics ranging from traditional researches, to sentence alignment, automatic word segmentation, POS tagging, and word sense disambiguation etc. In addition, analysis shows that the annotations and commentaries for Pre-Qin documents provides a novel and feasible resources for information processing with Pre-Qin documents, And it is found through research that Pre-Qin documents and its annotations and commentaries provide a new way and usable resources for information processing of Pre-Qin Chinese Corpus.

[Key Words]: Pre-Qin Chinese; annotations and commentaries; information processing

Introduction

In the history of Pre-Qin, Our ancestors created a brilliant history and civilization, during this period, Confucius, Mencius and other schools, started the first culture and academic prosperity in Chinese history. Many schools of thought, such as Confucian, Taoism, legalism, and Mohism came into being, together with masterpieces such as Lun Yu, Mencius, and Zuozhuang etc. Successive dynasties have made innumerable researches on them, which is of vital importance for passing on Chinese civilization.

As time went by, these scriptures or biographies distant them from readers of contemporary readers, and the words in Pre-Qin documents became unreadable to their off-springs. Therefore, the books of annotation appeared, which make interpretations of these Pre-Qin documents. Later on, as time passed by, and with a long time, language evolved and changed, these annotations are also not understood to Chinese people’s offsprings. Thus there’s a need to re-annotate and re-comment. These are called “shu”, which are books that make interpretations of old annotations. It can be said that for thousands of years, China has made great achievements in the researches of scriptures and their related annotations. Large amounts of annotations have not only ensured that scriptures will not be lost, but also promoted the development of the studies of the classics and the progress of civilization.

The development of software and hardware technology of computer and natural Language Processing Enables information processing with Mencius and other Pre-Qin documents and their annotations and comments. Moreover, tentative exploration has been made on sentence alignment, automatic word segmentation, POS tagging, and word sense disambiguation, which are different from modern Chinese information processing methods and means.

[16]Yu Lili. Research on Word Sense Disambiguation of Ancient Chinese Based on Conditional Random Field [J]. Microelectronics and Computer, 2009(10).

...