An object oriented multi robotic graphic simulation environment is described in this paper. Object oriented programming is used to model the physical objects of the robotic workcell in the form of software objects ...An object oriented multi robotic graphic simulation environment is described in this paper. Object oriented programming is used to model the physical objects of the robotic workcell in the form of software objects or classes. The virtual objects are defined to provide the user with a user friendly interface including realistic graphic simulation and clarify the software architecture. The programming method of associating the task object with active object effectively increases the software reusability, maintainability and modifiability. Task level programming is also demonstrated through a multi robot welding task that allows the user to concentrate on the most important aspects of the tasks. The multi thread programming technique is used to simulate the interaction of multiple tasks. Finally, a virtual test is carried out in the graphic simulation environment to observe design and program errors and fix them before downloading the software to the real workcell.展开更多
在机器阅读理解任务中,如何在包含不可回答问题的情况下提高答案的准确性是自然语言处理领域的一项重要挑战.虽然基于深度学习的机器阅读理解模型展现出很好的性能,但是这些模型仍然存在抽取特征冗余、语义信息不全面、问题分类任务和...在机器阅读理解任务中,如何在包含不可回答问题的情况下提高答案的准确性是自然语言处理领域的一项重要挑战.虽然基于深度学习的机器阅读理解模型展现出很好的性能,但是这些模型仍然存在抽取特征冗余、语义信息不全面、问题分类任务和答案抽取任务耦合性不强的问题.为了解决以上问题,本文提出一种结合门控机制和多级残差结构的多任务联合训练模型GMRT(Gated Mechanism and Multi-level Residual Structure for Multi-task Joint Training),以提升机器阅读理解任务中答案预测的准确性.GMRT构建门控机制来筛选交互后的关联特征,从而控制信息的流动.采用多级残差结构分别连接注意力机制和门控机制,保证每个阶段都保留原始语义信息.同时,通过边缘损失函数对问题分类任务和答案抽取任务联合训练,确保预测答案过程中任务之间的强耦合性.在SQuAD2.0数据集上的实验结果表明,GMRT模型的EM值和F1值均优于对比模型.展开更多
文摘An object oriented multi robotic graphic simulation environment is described in this paper. Object oriented programming is used to model the physical objects of the robotic workcell in the form of software objects or classes. The virtual objects are defined to provide the user with a user friendly interface including realistic graphic simulation and clarify the software architecture. The programming method of associating the task object with active object effectively increases the software reusability, maintainability and modifiability. Task level programming is also demonstrated through a multi robot welding task that allows the user to concentrate on the most important aspects of the tasks. The multi thread programming technique is used to simulate the interaction of multiple tasks. Finally, a virtual test is carried out in the graphic simulation environment to observe design and program errors and fix them before downloading the software to the real workcell.
文摘在机器阅读理解任务中,如何在包含不可回答问题的情况下提高答案的准确性是自然语言处理领域的一项重要挑战.虽然基于深度学习的机器阅读理解模型展现出很好的性能,但是这些模型仍然存在抽取特征冗余、语义信息不全面、问题分类任务和答案抽取任务耦合性不强的问题.为了解决以上问题,本文提出一种结合门控机制和多级残差结构的多任务联合训练模型GMRT(Gated Mechanism and Multi-level Residual Structure for Multi-task Joint Training),以提升机器阅读理解任务中答案预测的准确性.GMRT构建门控机制来筛选交互后的关联特征,从而控制信息的流动.采用多级残差结构分别连接注意力机制和门控机制,保证每个阶段都保留原始语义信息.同时,通过边缘损失函数对问题分类任务和答案抽取任务联合训练,确保预测答案过程中任务之间的强耦合性.在SQuAD2.0数据集上的实验结果表明,GMRT模型的EM值和F1值均优于对比模型.