Astronomical Knowledge Entity Extraction in Astrophysics Journal Articles via Large Language Models
作者机构:National Astronomical ObservatoriesChinese Academy of SciencesBeijing 100101China University of Chinese Academy of SciencesBeijing 100049China National Astronomical Data CenterBeijing 100101China Research Institute of Artificial IntelligenceZhejiang LabHangzhou 311100China Guilin UniversityGuangxi 541006China Xidian UniversityXi’an 710126China
出 版 物:《Research in Astronomy and Astrophysics》 (天文和天体物理学研究(英文版))
年 卷 期:2024年第24卷第6期
页 面:140-155页
核心收录:
学科分类:0502[文学-外国语言文学] 050201[文学-英语语言文学] 05[文学] 0704[理学-天文学]
基 金:supported by the National Natural Science Foundation of China(NSFC,Grant Nos.12273077,72101068,12373110,and 12103070) National Key Research and Development Program of China under grants(2022YFF0712400,2022YFF0711500) the 14th Five-year Informatization Plan of Chinese Academy of Sciences(CAS-WX2021SF-0204) supported by Astronomical Big Data Joint Research Center co-founded by National Astronomical Observatories,Chinese Academy of Sciences and Alibaba Cloud
主 题:astronomical databases:miscellaneous virtual observatory tools methods:data analysis
摘 要:Astronomical knowledge entities,such as celestial object identifiers,are crucial for literature retrieval and knowledge graph construction,and other research and applications in the field of *** methods of extracting knowledge entities from texts face numerous challenging obstacles that are difficult to ***,there is a pressing need for improved methods to efficiently extract *** study explores the potential of pre-trained Large Language Models(LLMs)to perform astronomical knowledge entity extraction(KEE)task from astrophysical journal articles using *** propose a prompting strategy called PromptKEE,which includes five prompt elements,and design eight combination prompts based on *** select four representative LLMs(Llama-2-70B,GPT-3.5,GPT-4,and Claude 2)and attempt to extract the most typical astronomical knowledge entities,celestial object identifiers and telescope names,from astronomical journal articles using these eight combination *** accommodate their token limitations,we construct two data sets:the full texts and paragraph collections of 30 *** the eight prompts,we test on full texts with GPT-4and Claude 2,on paragraph collections with all *** experimental results demonstrate that pre-trained LLMs show significant potential in performing KEE tasks,but their performance varies on the two data ***,we analyze some important factors that influence the performance of LLMs in entity extraction and provide insights for future KEE tasks in astrophysical articles using ***,compared to other methods of KEE,LLMs exhibit strong competitiveness in multiple aspects.