TY - GEN
T1 - RESIN
T2 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021
AU - Wen, Haoyang
AU - Lin, Ying
AU - Lai, Tuan Manh
AU - Pan, Xiaoman
AU - Li, Sha
AU - Lin, Xudong
AU - Zhou, Ben
AU - Li, Manling
AU - Wang, Haoyu
AU - Zhang, Hongming
AU - Yu, Xiaodong
AU - Dong, Alexander
AU - Wang, Zhenhailong
AU - Fung, Yi Ren
AU - Mishra, Piyush
AU - Lyu, Qing
AU - Surís, Dídac
AU - Chen, Brian
AU - Brown, Susan Windisch
AU - Palmer, Martha
AU - Callison-Burch, Chris
AU - Vondrick, Carl
AU - Han, Jiawei
AU - Roth, Dan
AU - Chang, Shih Fu
AU - Ji, Heng
N1 - Funding Information:
This research is based upon work supported in part by U.S. DARPA 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. We thank all the annotators who have contributed to the annotations of our training data for the joint IE component (in alphabetical order): Daniel Campos, Anthony Cuff, Yi R. Fung, Xiaodan Hu, Emma Bonnette Hamel, Samual Kriman, Meha Goyal Kumar, Manling Li, Tuan M. Lai, Ying Lin, Sarah Moeller, Ashley Nobi, Xiaoman Pan, Nikolaus Parulian, Adams Pollins, Rachel Rosset, Haoyu Wang, Qingyun Wang, Zhenhailong Wang, Spencer Whitehead, Lucia Yao, Pengfei Yu, Qi Zeng, Haoran Zhang, Hongming Zhang, Zixuan Zhang.
Publisher Copyright:
© 2021 Association for Computational Linguistics.
PY - 2021
Y1 - 2021
N2 - We present a new information extraction system that can automatically construct temporal event graphs from a collection of news documents from multiple sources, multiple languages (English and Spanish for our experiment), and multiple data modalities (speech, text, image and video). The system advances state-of-the-art from two aspects: (1) extending from sentence-level event extraction to cross-document cross-lingual cross-media event extraction, coreference resolution and temporal event tracking; (2) using human curated event schema library to match and enhance the extraction output. We have made the dockerlized system publicly available for research purpose at GitHub, with a demo video.
AB - We present a new information extraction system that can automatically construct temporal event graphs from a collection of news documents from multiple sources, multiple languages (English and Spanish for our experiment), and multiple data modalities (speech, text, image and video). The system advances state-of-the-art from two aspects: (1) extending from sentence-level event extraction to cross-document cross-lingual cross-media event extraction, coreference resolution and temporal event tracking; (2) using human curated event schema library to match and enhance the extraction output. We have made the dockerlized system publicly available for research purpose at GitHub, with a demo video.
UR - http://www.scopus.com/inward/record.url?scp=85108521203&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85108521203&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85108521203
T3 - NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Demonstrations
SP - 133
EP - 143
BT - NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
Y2 - 6 June 2021 through 11 June 2021
ER -