Abstract: A method for extracting a dam emergency event based on a dual attention mechanism is provided. The method includes: performing data preprocessing, building a dependency graph, building a dual attention network, and filling a document-level argument. The performing data preprocessing includes labeling a dam emergency corpus and encoding sentences. Building a dependency graph includes assisting a model to mine a syntactic relation based on a dependency. Building a dual attention network includes weighing and fusing an attention network based on a graph transformer network (GTN) and capturing key semantic information in the sentence. Filling a document-level argument includes filling a document-level argument by detecting a key sentence and ordering a semantic similarity. The method introduces a dependency and overcomes the long-range dependency problem based on the dual attention mechanism, thus achieving high identification accuracy and reducing a lot of labor costs.
Type:
Grant
Filed:
October 14, 2022
Date of Patent:
December 12, 2023
Assignees:
HOHAI UNIVERSITY, HUANENG LANCANG RIVER HYDROPOWER INC., HUANENG GROUP TECH INNOVATION CENTER CO., LTD.
Inventors:
Yingchi Mao, Wei Sun, Haibin Xiao, Fudong Chi, Hao Chen, Weiyong Zhan, Fugang Zhao, Han Fang, Xiaofeng Zhou, Chunrui Zhang, Bin Tan, Wenming Xie, Bingbing Nie, Zhixiang Chen, Chunrui Yang
Abstract: A method for extracting a dam emergency event based on a dual attention mechanism is provided. The method includes: performing data preprocessing, building a dependency graph, building a dual attention network, and filling a document-level argument. The performing data preprocessing includes labeling a dam emergency corpus and encoding sentences. Building a dependency graph includes assisting a model to mine a syntactic relation based on a dependency. Building a dual attention network includes weighing and fusing an attention network based on a graph transformer network (GTN) and capturing key semantic information in the sentence. Filling a document-level argument includes filling a document-level argument by detecting a key sentence and ordering a semantic similarity. The method introduces a dependency and overcomes the long-range dependency problem based on the dual attention mechanism, thus achieving high identification accuracy and reducing a lot of labor costs.
Type:
Application
Filed:
October 14, 2022
Publication date:
April 20, 2023
Applicants:
HOHAI UNIVERSITY, HUANENG LANCANG RIVER HYDROPOWER INC., HUANENG GROUP TECH INNOVATION CENTER CO., LTD.
Inventors:
Yong CHENG, Yingchi MAO, Haibin XIAO, Weiyong ZHAN, Hao CHEN, Longbao WANG, Fugang ZHAO, Han FANG, Xiaofeng ZHOU, Chunrui ZHANG, Bin TAN, Wenming XIE, Bingbing NIE, Zhixiang CHEN, Chunrui YANG