지능화 시대 속의 고전 문헌 자원의 개발과 이용 The Application of Artificial Intelligence on Chinese Classical Text 智能时代古典⽂献资源的开发与利⽤
- WANG Jun(王軍, Center for Digital Humanities at Peking University, China)
- SU Qi, SUN Xianbin. the
Center for Digital Humanities at Peking University, China
數十年來古籍數字化的發展產生了大量的數字化古籍文本。在大規模的古籍文本上可以應用深度學習、知識圖譜等人工智能技術深度開發與利用古籍文獻資源。本次報告將介紹北京大學近年來的相關研究成果，包括：應用深度學習方法實現從先秦到明清跨時代語料的自動句讀、自動標點和專有名詞識別；應用知識圖譜技術重構《宋元學案》並提供可視化瀏覽；應用GIS技術展現《朱熹年譜長編》。在此基礎上，未來的目標是構建智能化的古籍整理平臺和知識圖譜自動生成平臺，將數千年積纍的古籍文本轉化爲智能信息環境下可資利用的知識資源。
With the availability of the large volume Chinese ancient text collections, it becomes feasible to utilize deep learning, knowledge graph and GIS technologies upon the Chinese ancient text corpora and develop visualization applications to make the Chinese canonical texts accessible to public in Internet. In this talk, we will introduce some research projects undergoing in the Center of Digital Humanities at Peking University, including the 吾與點 platform for the automatic punctuation and named entity recognition of ancient Chinese texts, the visualized knowledge graph system for 《宋元學案》, and the reconstruction of 《朱熹年譜長編》 with GIS system. We are planning to build an AI-augmented online system for transforming ancient books into well-formed E-texts for open public use. |
