Example-Based Method for Machine Translation of Oracle Bone Inscriptions

Abstract

The invention discloses a carapace bone script explanation machine translation method based on an example, which comprises the steps of: (a) building to finish a carapace bone script explanation-modern Chinese language bilingual corpus; (b) finishing the sentence alignment, the phrase alignment and the word alignment of the bilingual corpus, and building a translation example library; (c) inputting a carapace bone script explanation to be translated; (d) on the basis of the translation example library built in step (b), carrying out full-example matching or parts-of-example matching retrieval to the input carapace bone script explanation to be translated; (e) displaying a final translation result to a user via a display; and (f) evaluating the translation result, and adding a bilingual sentence pair which satisfies a paraphrasing requirement into the translation example library. With the carapace bone script explanation machine translation method based on an example, which utilizes the storage and inquiry advantages of the computer, burden of carapace bone script experts is lightened, and a carapace bone script research threshold is lowered.

Description

technical field [0001] The invention relates to a natural language processing technology, in particular to an instance-based Oracle machine translation method. Background technique [0002] The primary problem facing oracle bone inscription research is how to use modern Chinese to understand and read oracle bone inscriptions. Experts on oracle bone inscriptions at home and abroad have pointed out that it is very meaningful to interpret oracle bone inscriptions in vernacular Chinese. However, the threshold for engaging in oracle bone inscription research is very high, and it takes ten to twenty years or even longer to train an oracle bone inscription expert, and the identification and translation of oracle bone inscriptions by experts rely on long-term academic research and experience accumulation, which is only stored in experts. The effective sharing of knowledge cannot be achieved in the minds of students. If computer technology and information technology can be used to i...

AI Technical Summary

Problems solved by technology

RBMT is rule-dependent, and its "bottleneck" is that the cost of obtaining large-scale language rules through manual writing is too high, and it is difficult to make greater breakthroughs in research. Moreover, Oracle is the earliest systemic language so far, and many grammatical rules still exist. It is in an uncertain state, so it is difficult to obtain and maintain the deep-level oracle bone rules; the SMT method needs a large-scale bilingual parallel corpus as the basis for training various probability parameters, but the scale of the oracle bone data collected is far from enough, and , the text on a piece of oracle bone is more than a hundred characters at most, and the least is only one character, the problem of data sparseness is serious

Images