No abstract

Abstract:Traveling surges are commonly adopted in protection devices of high-voltage direct current (HVDC) transmission systems. Lightning strikes also can produce large-amplitude traveling surges which lead to the malfunction of relays. To ensure the reliable operation of protection devices, recognition of traveling surges must be considered. Wavelet entropy, which can reveal time-frequency distribution features, is a potential tool for traveling surge recognition. In this paper, the effectiveness of wavelet entropy in characterizing traveling surges is demonstrated by comparing its representations of different kinds of surges and discussing its stability with the effects of propagation distance and fault resistance. A wavelet entropy-based recognition method is proposed and tested by simulated traveling surges. The results show wavelet entropy can discriminate fault traveling surges with a good recognition rate.

No abstract

Large scale pre-training models have been widely used in named entity recognition (NER) tasks. However, model ensemble through parameter averaging or voting can not give full play to the differentiation advantages of different models, especially in the open domain. This paper describes our NER system in the SemEval 2022 task11: MultiCoNER. We proposed an effective system to adaptively ensemble pre-trained language models by a Transformer layer. By assigning different weights to each model for different inputs, we adopted the Transformer layer to integrate the advantages of diverse models effectively. Experimental results show that our method achieves superior performances in Farsi and Dutch.

From pretrained contextual embedding to document-level embedding, the selection and construction of embedding have drawn more and more attention in the NER domain in recent research. This paper aims to discuss the performance of ensemble embeddings on complex NER tasks. Enlightened by Wang's methodology, we try to replicate the dominating power of ensemble models with reinforcement learning optimizor on plain NER tasks to complex ones. Based on the composition of semeval dataset, the performance of the applied model is tested on lower-context, QA, and search query scenarios together with its zero-shot learning ability. Results show that with abundant training data, the model can achieve similar performance on lower-context cases compared to plain NER cases, but can barely transfer the performance to other scenarios in the test phase.