Abstract Multi-task learning, in which several tasks are jointly learned by a single model, allows NLP models to share information from multiple annotations and may facilitate better predictions when the inter-related. This technique, however, requires annotating same text with annotation schemes, be costly laborious. Active learning (AL) has been demonstrated optimize processes iteratively sel...

The generalization ability of supervised model is relatively weak in keyword extraction technology. In order to effectively improve the robustness and accuracy model, key overcome this problem collect more data for training process. However, text as an privacy information, it harder collect. To solve problem, we apply federal learning use user locally performance. integrate unlabeled utterances...

One difficulty with existing theoretical work on HTN planning is that it does not address some of the planning constructs that are commonly used in HTN planners for practical applications. Although such constructs can make it difficult to ensure the soundness and completeness of HTN planning, they are important because they can greatly improve the efficiency of planning in practice. In this pap...

Introduction: The current study aimed at investigating the existence of the cross state-dependent learning between morphine and scopolamine (SCO) in mice by passive avoidance method, pointing to the role of CA1 area.  Methods: The effects of pre-training SCO (0.75, 1.5, and 3 μg, Intra-CA1), or morphine (1, 3, and 6 mg/kg, intraperitoneal (i.p.) was evaluated on the retrieval of passiv...

The aim of the present study was to investigate whether and by which mechanism; histamine can induce state-dependent retrieval of passive avoidance task. The pre-training or pre-test intracerebroventricular (i.c.v.) injection of histamine (20µg/mouse) impaired retrieval, when it was tested 24 h later. In the animals, which retrieval was impaired due to histamine pre-training administration, pre...