Shulou(Shulou.com)12/24 Report--

CTOnews.com, December 14, according to the "Nanjing Agricultural University Alumni Association" official account, the research team of Professor Wang Dongbo of the School of Information Management of Nanjing Agricultural University recently released the big language model of Xunzi's ancient books in Beijing.

According to reports, the great model of Xunzi includes the vast majority of ancient literature, including Siku Quanshu, and has a large corpus of more than 2 billion words. it is an intelligent tool for the processing and research of ancient books launched by the school team with the support of the national social science fund project "Cross-language knowledge Base Construction and Application Research of Chinese Ancient Books".

Nanjing Agricultural University says the model has the following highlights:

Intelligent indexing: can carry out high-quality topic indexing of the content in ancient books, helping researchers to quickly understand the topic of the article.

Information extraction: can automatically extract key information from ancient books, such as people, events, locations, etc., greatly saving information collation time

Poetry generation: can automatically generate ancient poems that meet grammatical rules and prosodic requirements according to a given theme or key words, so as to provide creative inspiration for poetry lovers.

High-quality translation: for difficult to understand ancient literature, accurate modern translation can be carried out to help researchers better understand the meaning of the original text.

Reading comprehension: be able to analyze and interpret the given ancient text and realize the automatic reading of the ancient text.

Lexical analysis: it can complete automatic word segmentation and part-of-speech tagging of ancient texts, and effectively improve the efficiency of research.

Automatic punctuation: it can quickly complete the broken sentences and punctuation of the ancient text, and enhance the user's reading experience of the ancient text.

The model consists of two parts: the pedestal model XunziALLM and the dialogue model XunziChat. Users can also fine-tune the pedestal model using local training corpus according to their own needs, so as to achieve better processing performance in the downstream processing tasks of ancient books.

The model has been released on GitHub and other websites as an open source public welfare research result. CTOnews.com attached a link: click here to go to

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.