Frontiers of Information Technology & Electronic Engineering
>> 2021,
Volume 22,
Issue 3
doi:
10.1631/FITEE.2000347
A survey of script learning
Affiliation(s): Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha 410000, China; Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410000, China; School of Data and Computer Science, Affilfontit Sun Yat-sen University, Guangzhou 510006, China; less
Received: 2020-07-13
Accepted: 2021-03-08
Available online: 2021-03-08
Next
Previous
Abstract
Script is the structured knowledge representation of prototypical real-life event sequences. Learning the commonsense knowledge inside the script can be helpful for machines in understanding natural language and drawing commonsensible inferences. is an interesting and promising research direction, in which a trained system can process narrative texts to capture script knowledge and draw inferences. However, there are currently no survey articles on , so we are providing this comprehensive survey to deeply investigate the standard framework and the major research topics on . This research field contains three main topics: event representations, models, and evaluation approaches. For each topic, we systematically summarize and categorize the existing systems, and carefully analyze and compare the advantages and disadvantages of the representative systems. We also discuss the current state of the research and possible future directions.
京公网安备 11010502051620号
