As a data augmentation method, masking word is commonly used in many natural language processing tasks. However, most mask methods are based on rules and are not related to downstream tasks. In this paper, we propose a novel masking word generator, named Actor-Critic Mask Model (ACMM), which can adaptively adjust the mask strategy according to the performance of downstream tasks. In order to demonstrate the effectiveness of the method, we conducted experiments on two causal event extraction datasets. Experiment results show that, compared with various rule-based masking methods, the masked sentences generated by our proposed method can significantly enhance the generalization of the model and improve the model performance.
Human behavior, due to its complexity, makes exploration of human behaviors very important and interesting. It is also because of the high complexity of human behavior, how to find and reveal the objective law has long attracted the research interest of scholars from sociology, psychology, economics, and other disciplines. With the rapid development of network technology, especially in recent years the online social network representative by personal online community, online dating network, social network has developed rapidly, the popularity of whose application directly lead to increase of the data amount, a large number of detailed user behavior data is recorded. Much data in online social network era gives us an unprecedented opportunity to study human behavior.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.