Search

Your search keyword '"Su, Zhong"' showing total 4,125 results
Start Over Author "Su, Zhong"
4,125 results on '"Su, Zhong"'

30. Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement

Author

Hu, Mengting, Guo, Honglei, Zhao, Shiwan, Gao, Hang, and Su, Zhong

Subjects
Computer Science - Computation and Language
Abstract

A mind-map is a diagram that represents the central concept and key ideas in a hierarchical way. Converting plain text into a mind-map will reveal its key semantic structure and be easier to understand. Given a document, the existing automatic mind-map generation method extracts the relationships of every sentence pair to generate the directed semantic graph for this document. The computation complexity increases exponentially with the length of the document. Moreover, it is difficult to capture the overall semantics. To deal with the above challenges, we propose an efficient mind-map generation network that converts a document into a graph via sequence-to-graph. To guarantee a meaningful mind-map, we design a graph refinement module to adjust the relation graph in a reinforcement learning manner. Extensive experimental results demonstrate that the proposed approach is more effective and efficient than the existing methods. The inference time is reduced by thousands of times compared with the existing methods. The case studies verify that the generated mind-maps better reveal the underlying semantic structures of the document., Comment: Accepted by EMNLP 2021 main conference

Published
2021

37. An unprecedented fully reduced {Mo V 60 } polyoxometalate: from an all-inorganic molecular light-absorber model to improved photoelectronic performance

Author

Li, Xue-Xin, Ji, Tuo, Gao, Jun-Yang, Chen, Wei-Chao, Yuan, Ye, Sha, Hao-Yan, Faller, Roland, Shan, Guo-Gang, Shao, Kui-Zhan, Wang, Xin-Long, and Su, Zhong-Min

Subjects
Affordable and Clean Energy, Chemical Sciences
Abstract

Fully reduced polyoxometalates are predicted to give rise to a broad and strong absorption spectrum, suitable energy levels, and unparalleled electronic and optical properties. However, they are not available to date. Here, an unprecedented fully reduced polyoxomolybdate cluster, namely Na8[MoV 60O140(OH)28]·19H2O {MoV 60}, was successfully designed and obtained under hydrothermal conditions, which is rare and is the largest fully reduced polyoxometalate reported so far. The MoV 60 molecule describes one Keggin {ε-Mo12} encapsulated in an unprecedented {Mo24} cage, giving rise to a double truncated tetrahedron quasi-nesting architecture, which is further face-capped by another four {Mo6} tripods. Its crystalline stability in air, solvent tolerance, and photosensitivity were all shown. As a cheap and robust molecular light-absorber model possessing wide light absorption, MoV 60 was applied to build a co-sensitized solar cell photoelectronic device along with N719 dyes and the optimal power conversion efficiency was 28% higher than that of single-dye sensitization. These results show that MoV 60 polyoxometalate could serve as an ideal model for the design and synthesis of all-inorganic molecular light-absorbers for other light-driven processes in the future.

Published
2022

38. Multi-Label Few-Shot Learning for Aspect Category Detection

Author

Hu, Mengting, Zhao, Shiwan, Guo, Honglei, Xue, Chao, Gao, Hang, Gao, Tiegang, Cheng, Renhong, and Su, Zhong

Subjects
Computer Science - Computation and Language
Abstract

Aspect category detection (ACD) in sentiment analysis aims to identify the aspect categories mentioned in a sentence. In this paper, we formulate ACD in the few-shot learning scenario. However, existing few-shot learning approaches mainly focus on single-label predictions. These methods can not work well for the ACD task since a sentence may contain multiple aspect categories. Therefore, we propose a multi-label few-shot learning method based on the prototypical network. To alleviate the noise, we design two effective attention mechanisms. The support-set attention aims to extract better prototypes by removing irrelevant aspects. The query-set attention computes multiple prototype-specific representations for each query instance, which are then used to compute accurate distances with the corresponding prototypes. To achieve multi-label inference, we further learn a dynamic threshold per instance by a policy network. Extensive experimental results on three datasets demonstrate that the proposed method significantly outperforms strong baselines., Comment: Accepted by ACL 2021 main conference

Published
2021

39. D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis

Author

Zheng, Yunhui, Pujar, Saurabh, Lewis, Burn, Buratti, Luca, Epstein, Edward, Yang, Bo, Laredo, Jim, Morari, Alessandro, and Su, Zhong

Subjects
Computer Science - Software Engineering, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Static analysis tools are widely used for vulnerability detection as they understand programs with complex behavior and millions of lines of code. Despite their popularity, static analysis tools are known to generate an excess of false positives. The recent ability of Machine Learning models to understand programming languages opens new possibilities when applied to static analysis. However, existing datasets to train models for vulnerability identification suffer from multiple limitations such as limited bug context, limited size, and synthetic and unrealistic source code. We propose D2A, a differential analysis based approach to label issues reported by static analysis tools. The D2A dataset is built by analyzing version pairs from multiple open source projects. From each project, we select bug fixing commits and we run static analysis on the versions before and after such commits. If some issues detected in a before-commit version disappear in the corresponding after-commit version, they are very likely to be real bugs that got fixed by the commit. We use D2A to generate a large labeled dataset to train models for vulnerability identification. We show that the dataset can be used to build a classifier to identify possible false alarms among the issues reported by static analysis, hence helping developers prioritize and investigate potential true positives first., Comment: Accepted to the 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP '21)

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results