SnO2-based electron transporting layer materials for perovskite solar cells: A review of recent progress

In recent years, due to their high photo-to-electric power conversion efficiency(PCE)(up to 23%(certified)) and low cost, perovskite solar cells(PSCs) have attracted a great deal of attention in photovoltaics field. The high PCE can be attributed to the excellent physical properties of organic–inorganic hybrid perovskite materials, such as a long charge diffusion length and a high absorption coefficient in the visible range. There are different diffusion lengths of holes in electrons in a PSC device, and thus the electron transporting layer(ETL) plays a critical role in the performance of PSCs. An alternative for TiO2, to the most common ETL material is SnO2, which has similar physical properties to TiO2 but with much higher electron mobility, which is beneficial for electron extraction. In addition, there are many facile methods to fabricate SnO2 nanomaterials with low cost and low energy consumption. In this review paper, we focus on recent developments in SnO2 as the ETL of PSCs. The fabrication methods of SnO2 materials are briefly introduced. The influence of multiple Sn O2 types in the ETL on the performance of PSCs is then reviewed. Different methods for improving the PCE and long-term stability of PSCs based on SnO2 ETL are also summarized. The review provides a systematic and comprehensive understanding of the influence of different Sn O2 ETL types on PSC performance and potentially motivates further development of PSCs with an extension to SnO2-based PSCs.

Towards Understanding Creative Language in Tweets

Extracting fine-grained information from social media is traditionally a challenging task, since the language used in social media messages is usually informal, with creative genre-specific terminology and expression. How to handle such a challenge so as to automatically understand the opinions that people are communicating has become a hot subject of research. In this paper, we aim to show that leveraging the pre-learned knowledge can help neural network models understand the creative language in Tweets. In order to address this idea, we present a transfer learning model based on BERT. We fine-turned the pre-trained BERT model and applied the customized model to two downstream tasks described in SemEval-2018: Irony Detection task and Emoji Prediction task of Tweets. Our model could achieve an F-score of 38.52 (ranked 1/49) in Emoji Prediction task and 67.52 (ranked 2/43) and 51.35 (ranked 1/31) in Irony Detection subtask A and subtask B. The experimental results validate the effectiveness of our idea.

Multi-Task Learning for Semantic Relatedness and Textual Entailment

Recently, several deep learning models have been successfully proposed and have been applied to solve different Natural Language Processing (NLP) tasks. However, these models solve the problem based on single-task supervised learning and do not consider the correlation between the tasks. Based on this observation, in this paper, we implemented a multi-task learning model to joint learn two related NLP tasks simultaneously and conducted experiments to evaluate if learning these tasks jointly can improve the system performance compared with learning them individually. In addition, a comparison of our model with the state-of-the-art learning models, including multi-task learning, transfer learning, unsupervised learning and feature based traditional machine learning models is presented. This paper aims to 1) show the advantage of multi-task learning over single-task learning in training related NLP tasks, 2) illustrate the influence of various encoding structures to the proposed single- and multi-task learning models, and 3) compare the performance between multi-task learning and other learning models in literature on textual entailment task and semantic relatedness task.