Event schemas encode knowledge of stereotypical structures of events and their connections. As events unfold, schemas are crucial to act as a scaffolding. Previous work on event schema induction focuses either on atomic events or linear temporal event sequences, ignoring the interplay between events via arguments and argument relations. We introduce a new concept of Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations. In addition, we propose a Temporal Event Graph Model that predicts event instances following the temporal complex event schema. To build and evaluate such schemas, we release a new schema learning corpus containing 6,399 documents accompanied with event graphs, and we have manually constructed gold-standard schemas. Intrinsic evaluations based on schema matching and instance graph perplexity, prove the superior quality of our probabilistic graph schema library compared to linear representations. Extrinsic evaluation on schema-guided future event prediction further demonstrates the predictive power of our event graph model, significantly outperforming human schemas and baselines by more than 23.8% on HITS@1.
SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China(信息工程研究所,中国科学院,北京,中国);School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China(网络安全学院,中国科学院大学,北京,中国);School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China(人工智能学院,中国科学院大学,北京,中国)
SHIELD: LLM-Driven Schema Induction for Predictive Analytics in EV Battery Supply Chain Disruptions
Carnegie Mellon University(卡内基梅隆大学);Columbia University(哥伦比亚大学);Georgia Institute of Technology(佐治亚理工学院);University of Michigan(密歇根大学);Boston University(波士顿大学)
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);JP Olive S&T Management LLC(JP Olive科技管理有限责任公司)
Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);The Private Sector Humanitarian Alliance(私营部门人道主义联盟);DEVCOM Army Research Laboratory(DEVCOM陆军研究实验室)
From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters
ETH Zürich(苏黎世联邦理工学院);University of Maryland(马里兰大学);MPI(马克斯·普朗克研究所);University of Toronto(多伦多大学);United Nations Office for Disaster Risk Reduction(联合国减少灾害风险办公室)
Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction
School of Computer Science, Beijing University of Posts and Telecommunications(北京邮电大学计算机学院);School of Automation Science and Electrical Engineering, Beihang University(北京航空航天大学自动化科学与电气工程学院);Beijing Institute of Computer Technology and Application(北京计算机技术及应用研究所);Inspur Group Co., Ltd.(浪潮集团有限公司);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)
Composite Monte Carlo Decision Making under High Uncertainty of Novel Coronavirus Epidemic Using Hybridized Deep Learning and Fuzzy Rule Induction
University of Macau(澳门大学);Zhuhai Institutes of Advanced Technology of the Chinese Academy of Sciences(中国科学院珠海先进技术研究院);Techno India College of Technology(印度Techno印度科技学院);Universidad Internacional de La Rioja(拉里奥哈国际大学);University of Granada(格拉纳达大学)