A major bottleneck in training end-to-end task-oriented dialog system is the lack of data. To utilize limited training data more efficiently, we propose Modular Supervision Network (MOSS), an encoder-decoder training framework that could incorporate supervision from various intermediate dialog system modules including natural language understanding, dialog state tracking, dialog policy learning and natural language generation. With only 60% of the training data, MOSS-all (i.e., MOSS with supervision from all four dialog modules) outperforms state-of-the-art models on CamRest676. Moreover, introducing modular supervision has even bigger benefits when the dialog task has a more complex dialog state and action space. With only 40% of the training data, MOSS-all outperforms the state-of-the-art model on a complex laptop network trouble shooting dataset, LaptopNetwork, that we introduced. LaptopNetwork consists of conversations between real customers and customer service agents in Chinese. Moreover, MOSS framework can accommodate dialogs that have supervision from different dialog modules at both framework level and model level. Therefore, MOSS is extremely flexible to update in real-world deployment.
A systematic study of polycrystalline La0.67Sr0.33MnO3 (LSMO) manganite coatings has been undertaken to analyse the effect of various particle sizes on the magnetic and electric transport properties. In order to acquire a series of samples with different particle sizes, the samples were prepared by a sol-gel method and were subjected to annealing at four different temperatures. With decreasing particle sizes, the magnetization decreases while the coercivity increases, which is attributed to the magnetically disordered surface layer. More attractively, the electrical transport properties can be systematically manipulated by particle sizes and so can the low field magnetoresistance (LFMR) values. Emphasis is placed on how the particle size affects the temperature dependence of resistivity, and three conduction models are explored to describe the transport behaviours in three temperature regions. A minimum resistivity is observed in the low temperature region in the presence and absence of a magnetic field, which can be mainly explained as due to the intergranular spin polarized tunneling (ISPT) through the grain boundaries (GBs) in polycrystalline materials.
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.