TY - GEN
T1 - Building an Event Extractor with Only a Few Examples
AU - Yu, Pengfei
AU - Zhang, Zixuan
AU - Voss, Clare
AU - May, Jonathan
AU - Ji, Heng
N1 - This research is based upon work supported in part by U.S. DARPA LORELEI Program No. HR0011-15-C-0115, U.S. DARPA AIDA Program No. FA8750-18-2-001and4 KAIROSProgram No. FA8750-19-2-100The4. viewsand conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the officialpolicies, either expressed or implied, of DARPA,or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.
This research is based upon work supported in part by U.S. DARPA LORELEI Program No. HR0011- 15-C-0115, U.S. DARPA AIDA Program No. FA8750-18-2-0014 and KAIROS Program No. FA8750-19-2-1004. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of DARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.
PY - 2022
Y1 - 2022
N2 - Supervised event extraction models require a substantial amount of training data to perform well. However, event annotation requires a lot of human effort and costs much time, which limits the application of existing supervised approaches to new event types. In order to reduce manual labor and shorten the time to build an event extraction system for an arbitrary event ontology, we present a new framework to train such systems much more efficiently without large annotations. Our event trigger labeling model uses a weak supervision approach, which only requires a set of keywords, a small number of examples and an unlabeled corpus, on which our approach automatically collects weakly supervised annotations. Our argument role labeling component performs zero-shot learning, which only requires the names of the argument roles of new event types. The source codes of our event trigger detection and event argument extraction models are publicly available for research purposes. We also release a dockerized system connecting the two models into an unified event extraction pipeline.
AB - Supervised event extraction models require a substantial amount of training data to perform well. However, event annotation requires a lot of human effort and costs much time, which limits the application of existing supervised approaches to new event types. In order to reduce manual labor and shorten the time to build an event extraction system for an arbitrary event ontology, we present a new framework to train such systems much more efficiently without large annotations. Our event trigger labeling model uses a weak supervision approach, which only requires a set of keywords, a small number of examples and an unlabeled corpus, on which our approach automatically collects weakly supervised annotations. Our argument role labeling component performs zero-shot learning, which only requires the names of the argument roles of new event types. The source codes of our event trigger detection and event argument extraction models are publicly available for research purposes. We also release a dockerized system connecting the two models into an unified event extraction pipeline.
UR - https://www.scopus.com/pages/publications/85137544333
UR - https://www.scopus.com/pages/publications/85137544333#tab=citedBy
U2 - 10.18653/v1/2022.deeplo-1.11
DO - 10.18653/v1/2022.deeplo-1.11
M3 - Conference contribution
AN - SCOPUS:85137544333
T3 - DeepLo 2022 - 3rd Workshop on Deep Learning Approaches for Low-Resource NLP, Proceedings of the DeepLo Workshop
SP - 102
EP - 109
BT - DeepLo 2022 - 3rd Workshop on Deep Learning Approaches for Low-Resource NLP, Proceedings of the DeepLo Workshop
A2 - Cherry, Colin
A2 - Fan, Angela
A2 - Foster, George
A2 - Haffari, Gholamreza
A2 - Khadivi, Shahram
A2 - Peng, Nanyun
A2 - Ren, Xiang
A2 - Shareghi, Ehsan
A2 - Swayamdipta, Swabha
PB - Association for Computational Linguistics (ACL)
T2 - 3rd Workshop on Deep Learning Approaches for Low-Resource NLP, DeepLo 2022
Y2 - 14 July 2022
ER -