Search

Your search keyword '"Chen, Bingfeng"' showing total 234 results
Start Over Author "Chen, Bingfeng"
234 results on '"Chen, Bingfeng"'

1. S$^2$GSL: Incorporating Segment to Syntactic Enhanced Graph Structure Learning for Aspect-based Sentiment Analysis

Author

Chen, Bingfeng, Ouyang, Qihan, Luo, Yongqi, Xu, Boyan, Cai, Ruichu, and Hao, Zhifeng

Subjects
Computer Science - Computation and Language
Abstract

Previous graph-based approaches in Aspect based Sentiment Analysis(ABSA) have demonstrated impressive performance by utilizing graph neural networks and attention mechanisms to learn structures of static dependency trees and dynamic latent trees. However, incorporating both semantic and syntactic information simultaneously within complex global structures can introduce irrelevant contexts and syntactic dependencies during the process of graph structure learning, potentially resulting in inaccurate predictions. In order to address the issues above, we propose S$^2$GSL, incorporating Segment to Syntactic enhanced Graph Structure Learning for ABSA. Specifically,S$^2$GSL is featured with a segment-aware semantic graph learning and a syntax-based latent graph learning enabling the removal of irrelevant contexts and dependencies, respectively. We further propose a self-adaptive aggregation network that facilitates the fusion of two graph learning branches, thereby achieving complementarity across diverse structures. Experimental results on four benchmarks demonstrate the effectiveness of our framework., Comment: ACL2024(main)

Published
2024

20. Selective Electrochemical Oxidation of Benzylic C–H to Benzylic Alcohols with the Aid of Imidazolium Radical Mediators

Author

Peng, Fangfang, primary, Xiang, Junfeng, additional, Qin, Huisheng, additional, Chen, Bingfeng, additional, Duan, Ran, additional, Zhao, Wenling, additional, Liu, Shiqiang, additional, Wu, Tianbin, additional, Yuan, Wenli, additional, Li, Qian, additional, Li, Jikun, additional, Kang, Xinchen, additional, and Han, Buxing, additional

Published
2023
Full Text
View/download PDF

25. Sentiment Target Extraction Based on CRFs with Multi-features for Chinese Microblog

Author

Chen, Bingfeng, Hao, Zhifeng, Cai, Ruichu, Wen, Wen, Du, Shenzhi, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Morishima, Atsuyuki, editor, Zhang, Rong, editor, Zhang, Wenjie, editor, Chang, Lijun, editor, Fu, Tom Z. J, editor, Liu, Kuien, editor, Yang, Xiaoyan, editor, Zhu, Jia, editor, and Zhang, Zhiwei, editor

Published
2016
Full Text
View/download PDF

29. Aerobic Oxidative Cleavage of C(OH)−C Bonds to Produce Aromatic Aldehydes Catalyzed by CuI−1,10‐phenanthroline Complex.

Author

Zhao, Ziwei, Zhang, Zhanrong, Meng, Qinglei, Chen, Bingfeng, Song, Jinliang, Liu, Huizhen, and Han, Buxing

Subjects
METAL catalysts, BONDS (Finance), HYDROXYL group, AROMATIC aldehydes, RENEWABLE natural resources, LIGNINS, RADICALS (Chemistry), LIGNIN structure
Abstract

Effective cleavage and functionalization of C(OH)−C bonds is of great importance for the production of value‐added chemicals from renewable biomass resources such as carbohydrates, lignin and their derivatives. The efficiency and selectivity of oxidative cleavage of C(OH)−C bonds are hindered by their inert nature and various side reactions associated with the hydroxyl group. The oxidative conversion of secondary alcohols to produce aldehydes is particularly challenging because the generated aldehydes tend to be over‐oxidized to acids or the other side products. Noble‐metal based catalysts are necessary to get satisfactory aldehyde yields. Herein, for the first time, the efficient aerobic oxidative conversion of secondary aromatic alcohols into aromatic aldehydes is reported using non‐noble metal catalysts and environmentally benign oxygen, without any additional base. It was found that CuI−1,10‐phenanthroline (Cu−phen) complex showed outstanding performance for the reactions. The C(OH)−C bonds of a diverse array of aromatic secondary alcohols were effectively cleaved and functionalized, selectively affording aldehydes with excellent yields. Detailed mechanism study revealed a radical mediated pathway for the oxidative reaction. We believe that the findings in this work will lead to many explorations in non‐noble metal catalyzed oxidative reactions. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

43. Embedding Logic Rules Into Recurrent Neural Networks

Author

Zhu Jian, Wen Wen, Ruichu Cai, Zhifeng Hao, Cai Xiaofeng, Chen Bingfeng, and Guangqiang Xie

Subjects
General Computer Science, logic rules, business.industry, Computer science, named entity recognition, General Engineering, RNN, Recurrent neural network, sentiment classification, Embedding, General Materials Science, Artificial intelligence, lcsh:Electrical engineering. Electronics. Nuclear engineering, business, Rule of inference, lcsh:TK1-9971
Abstract

Incorporating prior knowledge into recurrent neural network (RNN) is of great importance for many natural language processing tasks. However, most of the prior knowledge is in the form of structured knowledge and is difficult to be exploited in the existing RNN framework. By extracting the logic rules from the structured knowledge and embedding the extracted logic rule into the RNN, this paper proposes an effective framework to incorporate the prior information in the RNN models. First, we demonstrate that commonly used prior knowledge could be decomposed into a set of logic rules, including the knowledge graph, social graph, and syntactic dependence. Second, we present a technique to embed a set of logic rules into the RNN by the way of feedback masks. Finally, we apply the proposed approach to the sentiment classification and named entity recognition task. The extensive experimental results verify the effectiveness of the embedding approach. The encouraging results suggest that the proposed approach has the potential for applications in other NLP tasks.

Published
2019

Catalog

Books, media, physical & digital resources
See catalog results