检索结果-内蒙古大学图书馆

R2-Net: Relation of relation learning network for sentence semantic matching

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Kun Wu, Le Lv, Guangyi Wang, Meng Chen, Enhong Ruan, Shulan School of Computer Science and Information Engineering Hefei University of Technology China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China China

Sentence semantic matching is one of the fundamental tasks in natural language processing, which requires an agent to determine the semantic relation among input sentences. Recently, deep neural networks have achieved impressive performance in this area, especially BERT. Despite their effectiveness, most of these models treat output labels as meaningless one-hot vectors, underestimating the semantic information and guidance of relations that these labels reveal, especially for tasks with a small number of labels. To address this problem, we propose a Relation of Relation Learning Network (R2-Net) for sentence semantic matching. Specifically, we first employ BERT to encode the input sentences from a global perspective. Then a CNN-based encoder is designed to capture keywords and phrase information from a local perspective. To fully leverage labels for better relation information extraction, we introduce a self-supervised relation of relation classification task for guiding R2-Net to consider more about relations. Meanwhile, a triplet loss is employed to distinguish the intra-class and inter-class relations in a finer granularity. Empirical experiments on two sentence semantic matching tasks demonstrate the superiority of our proposed model. As a byproduct, we have released the codes to facilitate other researches. © 2020, CC BY.

关键词： Natural language processing systems

An improved method of algal-bloom discrimination in Taihu Lake using Sentinel-1A data 6

学校读者我要写书评

暂无评论

An improved method of algal-bloom discrimination in Taihu La...

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

作者： Wu, Lin Sun, Mengwei Min, Lin Zhao, Jianhui Li, Ning Guo, Zhengwei College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Kaifeng475004 China

ISBN: (纸本)9781728129129

The algal bloom is a prominent manifestation of water pollution. Synthetic aperture radar (SAR) shows an advantage in water monitoring due to its characteristic of all-time and all-weather. The water regions where algae gather present dark in SAR image. However, dark regions may also be caused by other factors, such as low wind. This paper proposes an improved algal bloom discrimination method based on Artificial Neural Network (ANN) to recognize the dark regions of algal bloom. Taihu Lake is chosen as the research area in this study because of its serious bloom in recent years. By means of quasi-synchronous optical images, the dark region database of SAR images labeled algal bloom and non-algal bloom are obtained. Then the segmentation algorithm and region growing algorithm are used to acquire the feature from dark regions, and divided into training feature set and testing feature set. Finally, the training and testing feature set are used for ANN-based discrimination model construction and verification. According the experimental results, the overall accuracy reaches 80%, which indicates that ANN model has a good applicability in algal bloom recognition of SAR image. © 2019 IEEE.

关键词： Neural networks

Chinese embedding via stroke and glyph information: A dual-channel view

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Taoy, Hanqing Tongy, Shiwei Xuyx, Tong Liuyx, Qi Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China School of Data Science University of Science and Technology of China

Recent studies have consistently given positive hints that morphology is helpful in enriching word embeddings. In this paper, we argue that Chinese word embeddings can be substantially enriched by the morphological information hidden in characters which is reflected not only in strokes order sequentially, but also in character glyphs spatially. Then, we propose a novel Dual-channel Word Embedding (DWE) model to realize the joint learning of sequential and spatial information of characters. Through the evaluation on both word similarity and word analogy tasks, our model shows its rationality and superiority in modelling the morphology of Chinese. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

Deep Technology Tracing for High-Tech Companies

学校读者我要写书评

暂无评论

Deep Technology Tracing for High-Tech Companies

IEEE International Conference on data Mining (ICDM)

作者： Han Wu Kun Zhang Guangyi Lv Qi Liu Runlong Yu Weihao Zhao Enhong Chen Jianhui Ma Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China

Technological change and innovation are vitally important, especially for high-tech companies. However, factors influencing their future research and development (R&D) trends are both complicated and various, leading it a quite difficult task to make technology tracing for high-tech companies. To this end, in this paper, we develop a novel data-driven solution, i.e., Deep Technology Forecasting (DTF) framework, to automatically find the most possible technology directions customized to each high-tech company. Specially, DTF consists of three components: Potential Competitor Recognition (PCR), Collaborative Technology Recognition (CTR), and Deep Technology Tracing (DTT) neural network. For one thing, PCR and CTR aim to capture competitive relations among enterprises and collaborative relations among technologies, respectively. For another, DTT is designed for modeling dynamic interactions between companies and technologies with the above relations involved. Finally, we evaluate our DTF framework on real-world patent data, and the experimental results clearly prove that DTF can precisely help to prospect future technology emphasis of companies by exploiting hybrid factors.

关键词：

Crowdfunding dynamics tracking: A reinforcement learning approach

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Jun Zhang, Hefu Liu, Qi Pan, Zhen Tao, Hanqing Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China

Recent years have witnessed the increasing interests in research of crowdfunding mechanism. In this area, dynamics tracking is a significant issue but is still under exploration. Existing studies either fit the fluctuations of time-series or employ regularization terms to constrain learned tendencies. However, few of them take into account the inherent decision-making process between investors and crowdfunding dynamics. To address the problem, in this paper, we propose a Trajectory-based Continuous Control for Crowdfunding (TC3) algorithm to predict the funding progress in crowdfunding. Specifically, actor-critic frameworks are employed to model the relationship between investors and campaigns, where all of the investors are viewed as an agent that could interact with the environment derived from the real dynamics of campaigns. Then, to further explore the in-depth implications of patterns (i.e., typical characters) in funding series, we propose to subdivide them into fast-growing and slow-growing ones. Moreover, for the purpose of switching from different kinds of patterns, the actor component of TC3 is extended with a structure of options, which comes to the TC3-Options. Finally, extensive experiments on the Indiegogo dataset not only demonstrate the effectiveness of our methods, but also validate our assumption that the entire pattern learned by TC3-Options is indeed the U-shaped one. Copyright © 2019, The Authors. All rights reserved.

关键词： Crowdsourcing

Rumor Detection with Hierarchical Recurrent Convolutional Neural Network 8th

学校读者我要写书评

暂无评论

Rumor Detection with Hierarchical Recurrent Convolutional Ne...

8th CCF International Conference on Natural Language Processing and Chinese Computing, NLPCC 2019

作者： Lin, Xiang Liao, Xiangwen Xu, Tong Pian, Wenjing Wong, Kam-Fai College of Mathematics and Computer Science Fuzhou University Fuzhou China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Hefei China The Chinese University of Hong Kong Sha Tin Hong Kong

ISBN: (纸本)9783030322359

Automatic rumor detection for events on online social media has attracted considerable attention in recent years. Usually, the events on social media are divided into several time segments, and for each segment, corresponding text will be converted as vectors for various neural network models to detect rumors. During this process, however, only sentence-level embedding has been considered, while the contextual information at the word level has been largely ignored. To address that issue, in this paper, we propose a novel rumor detection method based on a hierarchical recurrent convolutional neural network, which integrates contextual information for rumor detection. Specifically, with dividing events on social media into time segments, recurrent convolution neural network is adapted to learn the contextual representation information. Along this line, a bidirectional GRU network with attention mechanism is integrated to learn the time period information via combining event feature vectors. Experiments on real-world data sets validate that our solution could outperform several state-of-the-art methods. © 2019, Springer Nature Switzerland AG.

关键词： Convolution

EarthquakeAware: Visual Analytics for Understanding Human Impacts of Earthquakes from Social Media data

学校读者我要写书评

暂无评论

EarthquakeAware: Visual Analytics for Understanding Human Im...

IEEE Symposium on Visual Analytics Science and Technology (VAST)

作者： Shuai Chen Sihang Li Liwenhan Xie Yi Zhong Yun Han Xiaoru Yuan Key Laboratory of Machine Perception Ministry of Education School of EECS Peking University National Engineering Laboratory for Big Data Analysis and Application Peking University

In this paper, we propose EathquakeAware, a visual analytics system for social media visualization. Our system supports analyzing geo-tagged messages from different perspectives, including location, keyword, account. It can summarize the evolution patterns of topics and reveal the discussing trend of different keywords to help evaluate situations in different regions. We take VAST Challenge 2019 Mini Challenge 3 as case studies to demonstrate its effectiveness in a fictitious analysis scenario.

关键词：

Molecular property prediction: A multilevel quantum interactions modeling perspective

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Lu, Chengqiang Liu, Qi Wang, Chao Huang, Zhenya Lin, Peize He, Lixin Anhui Province Key Lab. of Big Data Analysis and Application University of SandT of China Key Laboratory of Quantum Information University of SandT of China

Predicting molecular properties (e.g., atomization energy) is an essential issue in quantum chemistry, which could speed up much research progress, such as drug designing and substance discovery. Traditional studies based on density functional theory (DFT) in physics are proved to be time-consuming for predicting large number of molecules. Recently, the machine learning methods, which consider much rule-based information, have also shown potentials for this issue. However, the complex inherent quantum interactions of molecules are still largely underexplored by existing solutions. In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction. Specifically, we represent each molecule as a graph to preserve its internal structure. Moreover, the well-designed hierarchical graph neural network directly extracts features from the conformation and spatial information followed by the multilevel interactions. As a consequence, the multilevel overall representations can be utilized to make the prediction. Extensive experiments on both datasets of equilibrium and off-equilibrium molecules demonstrate the effectiveness of our model. Furthermore, the detailed results also prove that MGCN is generalizable and transferable for the prediction. Copyright © 2019, The Authors. All rights reserved.

关键词： Molecules

Estimating early fundraising performance of innovations via graph-based market environment model

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wu, Likang Li, Zhi Zhao, Hongke Pan, Zhen Liu, Qi Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China College of Management and Economics Tianjin University

Well begun is half done. In the crowdfunding market, the early fundraising performance of the project is a concerned issue for both creators and platforms. However, estimating the early fundraising performance before the project published is very challenging and still under-explored. To that end, in this paper, we present a focused study on this important problem in a market modeling view. Specifically, we propose a Graph-based Market Environment model (GME) for estimating the early fundraising performance of the target project by exploiting the market environment. In addition, we discriminatively model the market competition and market evolution by designing two graph-based neural network architectures and incorporating them into the joint optimization stage. Finally, we conduct extensive experiments on the real-world crowdfunding data collected from ***. The experimental results clearly demonstrate the effectiveness of our proposed model for modeling and estimating the early fundraising performance of the target project. Copyright © 2019, The Authors. All rights reserved.

关键词： Crowdsourcing