TY - GEN
T1 - GENE
T2 - 15th Workshop on Graph-Based Methods for Natural Language Processing, TextGraphs 2021
AU - Zeng, Qi
AU - Li, Manling
AU - Lai, Tuan
AU - Ji, Heng
AU - Bansal, Mohit
AU - Tong, Hanghang
N1 - This research is based upon work supported in part by U.S. DARPA KAIROS Program No. FA8750-19-2-1004, U.S. DARPA AIDA Program No. FA8750-18-2-0014, Air Force No. FA8650-17-C-7715. 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 - 2021
Y1 - 2021
N2 - Current methods for event representation ignore related events in a corpus-level global context. For a deep and comprehensive understanding of complex events, we introduce a new task, Event Network Embedding, which aims to represent events by capturing the connections among events. We propose a novel framework, Global Event Network Embedding (GENE), that encodes the event network with a multi-view graph encoder while preserving the graph topology and node semantics. The graph encoder is trained by minimizing both structural and semantic losses. We develop a new series of structured probing tasks, and show that our approach effectively outperforms baseline models on node typing, argument role classification, and event coreference resolution.
AB - Current methods for event representation ignore related events in a corpus-level global context. For a deep and comprehensive understanding of complex events, we introduce a new task, Event Network Embedding, which aims to represent events by capturing the connections among events. We propose a novel framework, Global Event Network Embedding (GENE), that encodes the event network with a multi-view graph encoder while preserving the graph topology and node semantics. The graph encoder is trained by minimizing both structural and semantic losses. We develop a new series of structured probing tasks, and show that our approach effectively outperforms baseline models on node typing, argument role classification, and event coreference resolution.
UR - http://www.scopus.com/inward/record.url?scp=85129137213&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129137213&partnerID=8YFLogxK
U2 - 10.18653/v1/2021.textgraphs-1.5
DO - 10.18653/v1/2021.textgraphs-1.5
M3 - Conference contribution
AN - SCOPUS:85129137213
T3 - TextGraphs 2021 - Graph-Based Methods for Natural Language Processing, Proceedings of the 15th Workshop - in conjunction with the 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL 2021
SP - 42
EP - 53
BT - TextGraphs 2021 - Graph-Based Methods for Natural Language Processing, Proceedings of the 15th Workshop - in conjunction with the 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL 2021
A2 - Panchenko, Alexander
A2 - Malliaros, Fragkiskos D.
A2 - Logacheva, Varvara
A2 - Jana, Abhik
A2 - Ustalov, Dmitry
A2 - Jansen, Peter
PB - Association for Computational Linguistics (ACL)
Y2 - 11 June 2021
ER -