We apply a general deep learning framework to address the non-factoid question answering task. Our approach does not rely on any linguistic tools and can be applied to different languages or domains. Various architectures are presented and compared. We create and release a QA corpus and setup a new QA task in the insurance domain. Experimental results demonstrate superior performance compared to the baseline methods and various technologies give further improvements. For this highly challenging task, the top-1 accuracy can reach up to 65.3% on a test set, which indicates a great potential for practical use.

PSS are demonstrated in the optimized device due to the incorporation of an MoO3 layer.

Herein, we report the performance of CsPbX (X = Cl, Br, and I) perovskite quantum dots (QDs) for photocatalytic degradation of organic dyes. The photocatalytic performance of CsPbX QDs was characterized by UV-vis absorption spectra and ESI-MS, which evaluated their ability of degrading methyl orange (MO) solution under visible light irradiation. Interestingly, both CsPbCl and CsPbBr QDs show excellent photocatalytic activities, which can decompose the MO solution into a colorless solution within 100 min. This study demonstrates the potential of CsPbX QDs in the degradation of organic dyes and environmentally friendly applications. Moreover, the integration of CsPbX QDs and photocatalysis provides a new insight for the design of new photocatalysts.