Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] The classics are the carrier of Chinese traditional culture, thought and wisdom. Combining the methods of data acquisition, labeling and analysis of digital humanities, it is of great significance for the automatic entity recognition of classics for subsequent application research. [Method/process] The corpus was constructed based on 25 pre-Qin literature that have been automatically segmented and manually annotated, based on the corpus of different sizes and seven deep learning models of Bi-LSTM, Bi-LSTM-Attention, Bi-LSTM-CRF, Bi-LSTM-CRF-Attention, Bi-RNN, Bi-RNN-CRF and BERT, we extracted the corresponding entities that constituted historical events and compared their effects.[Result/conclusion] The accuracy of the Bi-LSTM-Attention and Bi-RNN-CRF models trained on all corpus reached 89.79% and 89.33%, respectively, confirming the feasibility of applying deep learning to large-scale text datasets.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-03-13
Zhang Zhixiong
Qian Li
Xie Jing
Chang Zhijun
Liu Yi
Yu Gaihong
Hu Maodi
Wang Lu
Li Xuesi
Zhao Yang
Wang Yufei
Wang Meng
Lin Xin
Zhang Mengting
Li Yang
Zhang Qin
Wang Yajiao
Guan Zhengyi
Meng Xu
Wu Xinyu
Abstract： ChatGPT is a dialogue system developed by OpenAI company. It appears as a Chatbot, but in essence, it uses Artificial Intelligence Generated Content (AIGC) technology to produce answers. Its key foundation is Generative Pre-trained Transformer and the core technology is InstructGPT. When compared to similar products in the early stages, its main characteristic is that there is a significant decrease in making up facts and generating toxic content. We present a systematic investigation of the technical structure, relevant research and practice, and applications scenarios of ChatGPT. Based on the investigation, we analyze the inspiration from the rapid development of AI technology as well as the influence of ChatGPT on Scientific Research and Library & Information Service. According to these influence, we present eight suggestions for the Library & Information Service field. Overall, the field should find its distinctive value orientation in the AI era, not only by maintaining the conventional scientific research paradigm, but also by exploring new technologies to boost scientific research.
Peer Review Status:
Awaiting Review
Hits
Hits
Downloads
Comment