Search

Your search keyword '"Yu, Bowen"' showing total 195 results
Start Over Author "Yu, Bowen" Search Limiters Academic (Peer-Reviewed) Journals
195 results on '"Yu, Bowen"'

15. Label Enhanced Event Detection with Heterogeneous Graph Attention Networks

Author

Cui, Shiyao, Yu, Bowen, Cong, Xin, Liu, Tingwen, Li, Quangang, and Shi, Jinqiao

Subjects
Computer Science - Computation and Language
Abstract

Event Detection (ED) aims to recognize instances of specified types of event triggers in text. Different from English ED, Chinese ED suffers from the problem of word-trigger mismatch due to the uncertain word boundaries. Existing approaches injecting word information into character-level models have achieved promising progress to alleviate this problem, but they are limited by two issues. First, the interaction between characters and lexicon words is not fully exploited. Second, they ignore the semantic information provided by event labels. We thus propose a novel architecture named Label enhanced Heterogeneous Graph Attention Networks (L-HGAT). Specifically, we transform each sentence into a graph, where character nodes and word nodes are connected with different types of edges, so that the interaction between words and characters is fully reserved. A heterogeneous graph attention networks is then introduced to propagate relational message and enrich information interaction. Furthermore, we convert each label into a trigger-prototype-based embedding, and design a margin loss to guide the model distinguish confusing event labels. Experiments on two benchmark datasets show that our model achieves significant improvement over a range of competitive baseline methods.

Published
2020
Full Text
View/download PDF

25. Cross-Domain NER under a Divide-and-Transfer Paradigm.

Author

Zhang, Xinghua, Yu, Bowen, Cong, Xin, Su, Taoyu, Li, Quangang, Liu, Tingwen, and Xu, Hongbo

Abstract

The article focuses on enhancing Cross-domain Named Entity Recognition (NER) by recognizing the discrepant transferability between entity detection and type prediction tasks. It introduces a novel paradigm called divide-and-transfer, employing separate functional modules for each task to improve domain transfer effectiveness.

Published
2024
Full Text
View/download PDF

42. Photonic Integrated Circuits for an Optical Phased Array.

Author

Yi, Yasha, Wu, Dachuan, Kakdarvishi, Venus, Yu, Bowen, Zhuang, Yating, and Khalilian, Alireza

Subjects
OPTICAL radar, LIDAR, INTEGRATED circuits
Abstract

Optical phased arrays (OPAs) are renowned for their exceptional ability to manipulate and direct light beams, positioning them as an ideal choice for solid-state light detection and ranging (LiDAR) technologies. This review provides a comprehensive examination of the current research landscape for photonic integrated circuit (PIC)-based OPAs. It begins by addressing the critical design elements at the component level necessary for optimal functionality. This review then delves into phase calibration techniques and the overarching architecture of OPAs. It concludes by emphasizing the innovative 3-D OPA design, which stands out for its enhanced optical efficiency. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

44. Single crystal synthesis and properties of the two-dimensional van der Waals frustrated magnets, Mn2In2Se5 and Mn2Ga2S5.

Author

Williams, Archibald J., Reifsnyder, Alexander, Yu, Bowen, Moore, Curtis E., Susner, Michael A., Windl, Wolfgang, McComb, David W., and Goldberger, Joshua E.

Abstract

There has been considerable interest in the search and design of two-dimensional (2D) van der Waals (vdW) compounds with exotic magnetic behavior. Here we establish the growth of phase pure crystals of Mn2In2Se5 and Mn2Ga2S5 and evaluate their structural, physical, and magnetic properties. These 2D vdW phases consist of double-octahedral thick Mn(S/Se)6 layers capped by InSe4 or GaS4 tetrahedra. Transmission electron microscopy confirms phase purity with the absence of impurity intergrowths of other closely related 2D vdW phases including Mn(In/Ga)2(Se/S)4 or In4Se3. Optical absorption measurements indicate these compounds have indirect band gaps of 1.33 and 1.58 eV, respectively. We also establish the Raman signatures for both compounds. Mn2In2Se5 and Mn2Ga2S5 are significantly frustrated magnetic materials due to the competing magnetic interactions in this double-thick triangular arrangement of metal atoms. They have magnetic transition temperatures of 7 and 13 K, respectively, compared to Weiss constants of −198 and −340 K, respectively. AC susceptibility experiments indicate that both Mn2In2Se5 and Mn2Ga2S5 exhibit significant spin glass character. The significant magnetic frustration makes these materials unique 2D magnetic vdW building blocks. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

46. A convolutional neural-network-based diagnostic framework for industrial bearing.

Author

Yu, Bowen and Xie, Chunli

Subjects
CONVOLUTIONAL neural networks, FAULT diagnosis, GENERALIZATION
Abstract

The problem of industrial bearing health monitoring and fault diagnosis has recently been a popular research topic. Extracting sufficient features from the input raw vibration signals and mapping them to the most likely fault labels is the essence of bearing fault diagnosis. This study proposes a novel framework for bearing defect diagnostics by merging dilated residual convolutional neural networks and attention mechanisms. In this framework, multiple parallel dilated convolutional networks can automatically learn rich fault features at each scale from vibration signals. Simultaneously, the attention approach boosts fault-related features and suppresses irrelevant ones, improving fault detection performance and generalization. According to the experimental results of two different bearing datasets, the framework achieves a higher accuracy and can accurately identify various types of faults. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results