Imparting human-like commonsense to machines is a long-term goal in the artificial intelligence community.To achieve this goal,constructing large-scale commonsense knowledge resources is an important step.In recent ye...Imparting human-like commonsense to machines is a long-term goal in the artificial intelligence community.To achieve this goal,constructing large-scale commonsense knowledge resources is an important step.In recent years,due to increasing demand,commonsense knowledge has become a rapidly growing research field,resulting in a surge of new acquisition methods and corresponding resources.These advances have empowered a variety of downstream AI tasks.However,constructing large-scale commonsense knowledge resources remains an ongoing and challenging task.It is still difficult to efficiently collect large-scale,high-quality commonsense knowledge.In this paper,we systematically review recent advances in commonsense knowledge acquisition methods and resources,providing a comprehensive summary of recent research scope,the characteristics of different resources,and unsolved challenges.展开更多
Collecting massive commonsense knowledge （CSK） for commonsense reasoning has been a long time standing challenge within artificial intelligence research. Numerous methods and systems for acquiring CSK have been deve...Collecting massive commonsense knowledge （CSK） for commonsense reasoning has been a long time standing challenge within artificial intelligence research. Numerous methods and systems for acquiring CSK have been developed to overcome the knowledge acquisition bottleneck. Although some specific commonsense reasoning tasks have been presented to allow researchers to measure and compare the performance of their CSK systems, we compare them at a higher level from the following aspects： CSK acquisition task （what CSK is acquired from where）, technique used （how can CSK be acquired）, and CSK evaluation methods （how to evaluate the acquired CSK）. In this survey, we first present a categorization of CSK acquisition systems and the great challenges in the field. Then, we review and compare the CSK acquisition systems in detail. Finally, we conclude the current progress in this field and explore some promising future research issues.展开更多
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 drawin...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.Script learning is an interesting and promising research direction,in which a trained script learning system can process narrative texts to capture script knowledge and draw inferences.However,there are currently no survey articles on script learning,so we are providing this comprehensive survey to deeply investigate the standard framework and the major research topics on script learning.This research field contains three main topics:event representations,script learning models,and evaluation approaches.For each topic,we systematically summarize and categorize the existing script learning 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.展开更多
基金supported by the National Key Research and Development Program of China(No.2020AAA 0106400)the National Natural Science Foundation of China(Nos.61976211 and 62176257)+1 种基金supported by the Strategic Priority Research Program of Chinese Academy of Sciences,China(No.XDA27020100)the Youth Innovation Promotion Association CAS,China,and Yunnan Provincial Major Science and Technology Special Plan Projects,China(No.202202AD 080004).
文摘Imparting human-like commonsense to machines is a long-term goal in the artificial intelligence community.To achieve this goal,constructing large-scale commonsense knowledge resources is an important step.In recent years,due to increasing demand,commonsense knowledge has become a rapidly growing research field,resulting in a surge of new acquisition methods and corresponding resources.These advances have empowered a variety of downstream AI tasks.However,constructing large-scale commonsense knowledge resources remains an ongoing and challenging task.It is still difficult to efficiently collect large-scale,high-quality commonsense knowledge.In this paper,we systematically review recent advances in commonsense knowledge acquisition methods and resources,providing a comprehensive summary of recent research scope,the characteristics of different resources,and unsolved challenges.
基金supported by the National Natural Science Foundation of China under Grant Nos.91224006,61173063,61035004,61203284,and 309737163the National Social Science Foundation of China under Grant No.10AYY003
文摘Collecting massive commonsense knowledge （CSK） for commonsense reasoning has been a long time standing challenge within artificial intelligence research. Numerous methods and systems for acquiring CSK have been developed to overcome the knowledge acquisition bottleneck. Although some specific commonsense reasoning tasks have been presented to allow researchers to measure and compare the performance of their CSK systems, we compare them at a higher level from the following aspects： CSK acquisition task （what CSK is acquired from where）, technique used （how can CSK be acquired）, and CSK evaluation methods （how to evaluate the acquired CSK）. In this survey, we first present a categorization of CSK acquisition systems and the great challenges in the field. Then, we review and compare the CSK acquisition systems in detail. Finally, we conclude the current progress in this field and explore some promising future research issues.
基金Project supported by the National Natural Science Foundation of China(No.61806216)。
文摘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.Script learning is an interesting and promising research direction,in which a trained script learning system can process narrative texts to capture script knowledge and draw inferences.However,there are currently no survey articles on script learning,so we are providing this comprehensive survey to deeply investigate the standard framework and the major research topics on script learning.This research field contains three main topics:event representations,script learning models,and evaluation approaches.For each topic,we systematically summarize and categorize the existing script learning 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.
