W Xiang, B Wang - IEEE Access, 2019 - ieeexplore.ieee.org
Numerous important events happen everyday and everywhere but are reported in different media sources with different narrative styles. How to detect whether real-world events have …
Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained …
X Li, F Li, L Pan, Y Chen, W Peng, Q Wang… - … Processing and Chinese …, 2020 - Springer
This paper introduces DuEE, a new dataset for Chinese event extraction (EE) in real-world scenarios. DuEE has several advantages over previous EE datasets.(1) Scale: DuEE …
R Chen, C Qin, W Jiang, D Choi - … of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Event extraction is an important task in natural language processing that focuses on mining event-related information from unstructured text. Despite considerable advancements, it is …
J Sheng, S Guo, B Yu, Q Li, Y Hei, L Wang… - arXiv preprint arXiv …, 2021 - arxiv.org
Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts. Most existing methods assume that events appear in sentences without …
MH Tong, B Xu, S Wang, M Han, Y Cao, J Zhu, S Chen… - 2022 - ink.library.smu.edu.sg
Event extraction aims to identify an event and then extract the arguments participating in the event. Despite the great success in sentencelevel event extraction, events are more …
H Yang, D Sui, Y Chen, K Liu, J Zhao… - Proceedings of the 59th …, 2021 - aclanthology.org
Document-level event extraction (DEE) is indispensable when events are described throughout a document. We argue that sentence-level extractors are ill-suited to the DEE …
H Cao, J Li, F Su, F Li, H Fei, S Wu, B Li… - arXiv preprint arXiv …, 2022 - arxiv.org
Event extraction (EE) is an essential task of information extraction, which aims to extract structured event information from unstructured text. Most prior work focuses on extracting flat …
Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning. However, existing pre-training methods have not involved modeling event …