We present in this paper a model for forecasting short-term electric load based on deep residual networks. The proposed model is able to integrate domain knowledge and researchers' understanding of the task by virtue of different neural network building blocks. Specifically, a modified deep residual network is formulated to improve the forecast results. Further, a two-stage ensemble strategy is used to enhance the generalization capability of the proposed model. We also apply the proposed model to probabilistic load forecasting using Monte Carlo dropout. Three public datasets are used to prove the effectiveness of the proposed model. Multiple test cases and comparison with existing models show that the proposed model is able to provide accurate load forecasting results and has high generalization capability.Index Terms-Short-term load forecasting, deep learning, deep residual network, probabilistic load forecasting.
Chinese Spelling Check (CSC) is a task to detect and correct spelling errors in Chinese natural language. Existing methods have made attempts to incorporate the similarity knowledge between Chinese characters. However, they take the similarity knowledge as either an external input resource or just heuristic rules. This paper proposes to incorporate phonological and visual similarity knowledge into language models for CSC via a specialized graph convolutional network (SpellGCN). The model builds a graph over the characters, and SpellGCN is learned to map this graph into a set of inter-dependent character classifiers. These classifiers are applied to the representations extracted by another network, such as BERT, enabling the whole network to be end-to-end trainable. Experiments 1 are conducted on three human-annotated datasets. Our method achieves superior performance against previous models by a large margin.
Numerical reasoning over texts, such as addition, subtraction, sorting and counting, is a challenging machine reading comprehension task, since it requires both natural language understanding and arithmetic computation. To address this challenge, we propose a heterogeneous graph representation for the context of the passage and question needed for such reasoning, and design a question directed graph attention network to drive multi-step numerical reasoning over this context graph. Our model, which combines deep learning and graph reasoning, achieves remarkable results in benchmark datasets such as DROP 1 . * Corresponding author 1 https://leaderboard.allenai.org/drop/submissions/public. As of September 08, 2020, our models are ranked first in the case of fair comparison using the identical pre-training model.
A series of mesoporous graphitic
carbon nitride (mg-C3N4) materials have been
prepared with urea and tetraethylorthosilicate
(TEOS) as the precursors, which were thermally polycondensed to obtain
the g-C3N4/silica composites, after silica was
removed, mg-C3N4 with large surface area (170
m2 g–1) was successfully prepared. Excitingly,
TEOS did not only act as a mesoporous-directing agent but also as
the promoter for the urea polycondensation to g-C3N4, which made the urea polycondensation proceed at relatively
low temperature. Thus, volatilization or/and decomposition of urea
in the process of thermal treatment were reduced, resulting in the
product yield of g-C3N4 from 0.3 to 0.4 g/10
g urea remarkably increasing to 1.2 g/10 g urea. Moreover, superior
photocatalytic activities were observed for degrading methyl orange
(MO) and H2 generation from water splitting over the mg-C3N4 photocatalyst. The facilely developed method
for high-yield mesoporous g-C3N4 from cost-effective
urea was more attractive for its wide applications in environmental
treatment and energy development fields.
A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper. Gated linear unit convolutional layers are used to extract information from the sequences of aggregate electricity consumption. Residual blocks are also introduced to refine the output of the neural network. The partially overlapped output sequences of the network are averaged to produce the final output of the model. We apply the proposed model to the REDD dataset and compare it with the convolutional sequence to point model in the literature. Results show that the proposed model is able to give satisfactory disaggregation performance for appliances with varied characteristics.Index Terms-Non-intrusive load monitoring, convolutional network, sequence to sequence learning, gated linear unit.
Aspect-term sentiment analysis (ATSA) is a long-standing challenge in natural language processing. It requires fine-grained semantical reasoning about a target entity appeared in the text. As manual annotation over the aspects is laborious and time-consuming, the amount of labeled data is limited for supervised learning. This paper proposes a semisupervised method for the ATSA problem by using the Variational Autoencoder based on Transformer. The model learns the latent distribution via variational inference. By disentangling the latent representation into the aspect-specific sentiment and the lexical context, our method induces the underlying sentiment prediction for the unlabeled data, which then benefits the ATSA classifier. Our method is classifier-agnostic, i.e., the classifier is an independent module and various supervised models can be integrated. Experimental results are obtained on the SemEval 2014 task 4 and show that our method is effective with different five specific classifiers and outperforms these models by a significant margin.
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.