Scientific and technological advancements enable the preservation and dissemination of traditional knowledge and culture, making innovations keys to the sustainability of our cultural heritage. A pioneering research project at The Hong Kong Polytechnic University (PolyU) promotes the synergy between scientific technologies and humanities, applying interdisciplinary approaches to make cultural heritage relevant today.
By distilling and formally representing geographic and ecological knowledge from ancient texts, the project aims to overcome the limitations of traditional text studies. It offers novel solutions that allow the digitisation of ancient texts to enable the transmission of knowledge, including visually presenting ancient geographical and ecological information.
The project entitled "Knowledge Integration of the Classic of Mountains and Seas: Reconstructing Ancient Ecological and Geographical Knowledge Heritage with Artificial Intelligence" is led by Prof. HUANG Chu-ren, Chair Professor of Applied Chinese Language Studies of the Department of Chinese and Bilingual Studies of PolyU. The project has been awarded as one of the "Top 10 Innovative Exploratory Projects" in Tencent’s "Tanyuan Scheme 2024”.
The new “Innovation and Exploration Track” of the Tanyuan Scheme received a total of 79 submissions from 48 universities and research institutes. The PolyU team is one of the five shortlisted and the only one awarded from Hong Kong and Macao. The expert jury commended the PolyU project for effiectively addressing the limitations of traditional textual research through visualisation and its innovative approach “to build a digital knowledge integration platform and provide a new way for digitising classical texts.”
The "Classic of Mountains (Shanjing)" is the first part of the pre-Qin classic text “Classic of Mountains and Seas (Shanhaijing).” Its text consists of approximately 20,000 characters of geographic information of mountains and rivers, as well as the natural resources therein. It is regarded as China's earliest attested compendium of geo-ecological information. Up-to-date, existing studies of the text remain within the classical humanities paradigm. Prof. HUANG's proposed research takes a knowledge integration approach to present an innovative solution for modernising and transmitting the knowledge content of "The Classic of Mountains."
Subsequently, the research team will apply artificial intelligence (AI) technologies such as information extraction, knowledge graphs, graph retrieval-augmented generation (RAG), and LLM to analyse, organise, integrate, and present the geographical and ecological knowledge contained in the Shanjing. The ultimate goal is to establish a “blueprint” for a platform to support the diachronic geo-ecological knowledge systems of China over the past two millennia to study the changes and variations through time and to provide the appropriate environmental information to understand historical events. As a stepping stone, the team will create a Q&A platform that consolidates information about the landmarks in Shanjing based on documentation from all dynasties, along with developing a digital map that visually illustrates the geographical features described in the text.
Prof. HUANG is the first Chinese permanent member of the International Committee for Computational Linguistics (ICCL) and ranks among the top 2% of scientists worldwide in the field of AI. His team members include Ms. Ke Liang, a PhD student, and Dr Xuemei Tang, a postdoctoral researcher. In addition, Dr Qi Su, Associate Professor from the Digital Humanities Center at Peking University, and Dr Jinghang GU, Research Assistant Professor of the Department of Chinese and Bilingual Studies of PolyU are co-principal investigators.
Prof. HUANG said, "The traditional knowledge of geography and ecology is crucial for our understanding of our past and how our environment changed. Contemporary ecological governance can also be benefit from understanding past changes. This project represents an interdisciplinary effort to integrate digital technology with the humanities, addressing the challenges of fragmentation and reusability of traditional knowledge, thereby enabling the transmission, integration and application of historical knowledge in contemporary contexts."