检索结果-内蒙古大学图书馆

Adaptive information seeking for open-domain question answering

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhu, Yunchang Pang, Liang Lan, Yanyan Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Institute for AI Industry Research Tsinghua University

Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus. Recently, iterative approaches have been proven to be effective for complex questions, by recursively retrieving new evidence at each step. However, almost all existing iterative approaches use predefined strategies, either applying the same retrieval function multiple times or fixing the order of different retrieval functions, which cannot fulfill the diverse requirements of various questions. In this paper, we propose a novel adaptive information-seeking strategy for open-domain question answering, namely AISO. Specifically, the whole retrieval and answer process is modeled as a partially observed Markov decision process, where three types of retrieval operations (e.g., BM25, DPR, and hyperlink) and one answer operation are defined as actions. According to the learned policy, AISO could adaptively select a proper retrieval action to seek the missing evidence at each step, based on the collected evidence and the reformulated query, or directly output the answer when the evidence set is sufficient for the question. Experiments on SQuAD Open and HotpotQA fullwiki, which serve as single-hop and multi-hop open-domain QA benchmarks, show that AISO outperforms all baseline methods with predefined strategies in terms of both retrieval and answer evaluations. © 2021, CC BY.

关键词： Hypertext systems

MatchZoo: A Learning, Practicing, and Developing System for Neural Text Matching

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Guo, Jiafeng Fan, Yixing Ji, Xiang Cheng, Xueqi University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China Beijing Institute of Technology University Beijing China

Text matching is the core problem in many natural language processing (NLP) tasks, such as information retrieval, question answering, and conversation. Recently, deep leaning technology has been widely adopted for text matching, making neural text matching a new and active research domain. With a large number of neural matching models emerging rapidly, it becomes more and more difficult for researchers, especially those newcomers, to learn and understand these new models. Moreover, it is usually difficult to try these models due to the tedious data pre-processing, complicated parameter configuration, and massive optimization tricks, not to mention the unavailability of public codes sometimes. Finally, for researchers who want to develop new models, it is also not an easy task to implement a neural text matching model from scratch, and to compare with a bunch of existing models. In this paper, therefore, we present a novel system, namely MatchZoo, to facilitate the learning, practicing and designing of neural text matching models. The system consists of a powerful matching library and a user-friendly and interactive studio, which can help researchers: 1) to learn state-of-the-art neural text matching models systematically, 2) to train, test and apply these models with simple configurable steps;and 3) to develop their own models with rich APIs and assistance. Copyright © 2019, The Authors. All rights reserved.

关键词： Natural language processing systems

Interactive key-Value Memory-augmented Attention for Image Paragraph Captioning 28

学校读者我要写书评

暂无评论

Interactive Key-Value Memory-augmented Attention for Image P...

28th International Conference on Computational Linguistics, COLING 2020

作者： Xu, Chunpu Li, Yu Li, Chengming Ao, Xiang Yang, Min Tian, Jinwen Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Huazhong University of Science and Technology China Shanghai Jiao Tong University China Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

ISBN: (纸本)9781952148279

Image paragraph captioning (IPC) aims to generate a fine-grained paragraph to describe the visual content of an image. Significant progress has been made by deep neural networks, in which the attention mechanism plays an essential role. However, conventional attention mechanisms tend to ignore the past alignment information, which often results in problems of repetitive captioning and incomplete captioning. In this paper, we propose an Interactive key-value Memory-augmented Attention model for image Paragraph captioning (IMAP) to keep track of the attention history (salient objects coverage information) along with the update-chain of the decoder state and therefore avoid generating repetitive or incomplete image descriptions. In addition, we employ an adaptive attention mechanism to realize adaptive alignment from image regions to caption words, where an image region can be mapped to an arbitrary number of caption words while a caption word can also attend to an arbitrary number of image regions. Extensive experiments on a benchmark dataset (i.e., Stanford) demonstrate the effectiveness of our IMAP model. © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Deep neural networks

The Adaptive Fault-tolerant Routing Based on an Improved Local Security Information Model of the Exchanged Hypercube 21

学校读者我要写书评

暂无评论

The Adaptive Fault-tolerant Routing Based on an Improved Loc...

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big data and Cloud computing, 16th IEEE International Conference on Social computing and networking and 13th International Conference on Sustainable computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Zhang, Yazhi Luo, Chuanwen Wang, Guijuan Zhang, Li Lv, Mengjie Yu, Jiguo Qilu University of Technology School of Computer Science and Technology Jinan China Beijing Forestry University School of Information Science and Technology Beijing China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Nanjing University of Posts and Telecommunications College of Computer Nanjing China Qilu University of Technology Shandong Academy of Sciences Big Data Research Institute Jinan China

ISBN: (纸本)9798350329223

With the increasing amount of computation in high-performance computing, the scale of interconnection networks is becoming larger and larger. It is inevitable that processors or links in the network become faulty. Therefore, it is very important for a processor to understand the security status of itself and neighbors, and then adaptively and reliably communicate. However, the existing security information models consider faulty processors or faulty links separately, and do not consider the situation where both processors and links fail simultaneously. The Exchanged Hypercube is an excellent interconnection network structure which achieves a balance between network functionality and hardware overhead while preserving many excellent properties of the Hypercube. In this paper, we propose an adaptive fault-tolerant routing algorithm of the Exchanged Hypercube based on an improved local security information model, which considers the faulty processors and faulty links simultaneously. This algorithm always can select suitable processors for routing based on the local security information and unsafe coefficients of processors, which greatly reduces the impact of the faulty of networks. The adaptive fault-tolerant routing algorithm of the Exchanged Hypercube network is not only suitable for regular networks but also for heterogeneous networks since the Exchanged Hypercube is a semi regular network. Sufficient experimental results show that the algorithm proposed in this paper has a lower packet loss rate, a higher success rate, and a shorter average path length. © 2023 IEEE.

关键词： Hypercube networks

A small-footprint accelerator for large-scale neural networks

学校读者我要写书评

暂无评论

A small-footprint accelerator for large-scale neural network...

作者： Chen, Tianshi Zhang, Shijin Liu, Shaoli Du, Zidong Luo, Tao Gao, Yuan Liu, Junjie Wang, Dongsheng Wu, Chengyong Sun, Ninghui Chen, Yunji Temam, Olivier State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China TNLIST Tsinghua University Beijing100084 China Inria Saclay France CAS Center for Excellence in Brain Science China

Machine-learning tasks are becoming pervasive in a broad range of domains, and in a broad range of systems (from embedded systems to data centers). At the same time, a small set of machine-learning algorithms (especially Convolutional and Deep Neural networks, i.e., CNNs and DNNs) are proving to be state-of-theart across many applications. As architectures evolve toward heterogeneous multicores composed of a mix of cores and accelerators, a machine-learning accelerator can achieve the rare combination of efficiency (due to the small number of target algorithms) and broad application scope. Until now, most machine-learning accelerator designs have been focusing on efficiently implementing the computational part of the algorithms. However, recent state-of-the-art CNNs and DNNs are characterized by their large size. In this study, we design an accelerator for large-scale CNNs and DNNs, with a special emphasis on the impact of memory on accelerator design, performance, and energy. We show that it is possible to design an accelerator with a high throughput, capable of performing 452 GOP/s (key NN operations such as synaptic weight multiplications and neurons outputs additions) in a small footprint of 3.02mm2 and 485mW;compared to a 128-bit 2GHz SIMD processor, the accelerator is 117.87?faster, and it can reduce the total energy by 21.08×. The accelerator characteristics are obtained after layout at 65nm. Such a high throughput in a small footprint can open up the usage of state-of-the-art machine-learning algorithms in a broad set of systems and for a broad set of applications. © 2015 ACM.

关键词： Deep neural networks

Transformation driven visual reasoning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hong, Xin Lan, Yanyan Pang, Liang Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Institute for AI Industry Research Tsinghua University Beijing China

This paper defines a new visual reasoning paradigm by introducing an important factor, i.e. transformation. The motivation comes from the fact that most existing visual reasoning tasks, such as CLEVR in VQA, are solely defined to test how well the machine understands the concepts and relations within static settings, like one image. We argue that this kind of state driven visual reasoning approach has limitations in reflecting whether the machine has the ability to infer the dynamics between different states, which has been shown as important as state-level reasoning for human cognition in Piaget’s theory. To tackle this problem, we propose a novel transformation driven visual reasoning task. Given both the initial and final states, the target is to infer the corresponding single-step or multi-step transformation, represented as a triplet (object, attribute, value) or a sequence of triplets, respectively. Following this definition, a new dataset namely TRANCE is constructed on the basis of CLEVR, including three levels of settings, i.e. Basic (single-step transformation), Event (multi-step transformation), and View (multi-step transformation with variant views). Experimental results show that the state-of-the-art visual reasoning models perform well on Basic, but are still far from human-level intelligence on Event and View. We believe the proposed new paradigm will boost the development of machine visual reasoning. More advanced methods and real data need to be investigated in this direction. The resource of TVR is available at https://***/TVR. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

A compound fault diagnosis method based on Multi-task Learning with Multi-gate Mixture-of-Experts 14

学校读者我要写书评

暂无评论

A compound fault diagnosis method based on Multi-task Learni...

14th International Conference on Measuring technology and Mechatronics Automation, ICMTMA 2022

作者： Chen, Yanping Ren, Lele Xia, Hong Wang, Zhongmin Gao, Cong Wang, Fengwei School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China ZTE Corporation No.55 Hi-techRoadSouth Shenzhen518057 China

ISBN: (纸本)9781665499781

At present, the research object of fault diagnosis focuses on single fault diagnosis. This method of diagnosis does not consider the relationship between mechanical equipment faults, and cannot fully identify the type of fault. In the actual industrial process, mechanical equipment is mostly complex system, and compound fault diagnosis is more in line with industrial needs. In order to solve the problem of compound fault diagnosis of mechanical equipment and improve the accuracy of fault identification, this paper establishes a compound fault diagnosis model for gearbox by means of multi-task learning, uses multi-gated networks to extract features from the task sharing layer, and finally classifies the fault through the task specific *** experimental results show that, the compound fault diagnosis method based on Multi-task Learning with Multi-gate Mixture-of-Experts (ML-MMoE) can accurately identify compound fault types under different working conditions. © 2022 IEEE

关键词： Failure analysis

Match-ignition: Plugging PageRank into transformer for long-form text matching

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Pang, Liang Lan, Yanyan Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute for AI Industry Research Tsinghua University Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Neural text matching models have been widely used in community question answering, information retrieval, and dialogue. However, these models designed for short texts cannot well address the long-form text matching problem, because there are many contexts in long-form texts can not be directly aligned with each other, and it is difficult for existing models to capture the key matching signals from such noisy data. Besides, these models are computationally expensive for simply use all textual data indiscriminately. To tackle the effectiveness and efficiency problem, we propose a novel hierarchical noise filtering model, namely Match-Ignition. The main idea is to plug the well-known PageRank algorithm into the Transformer, to identify and filter both sentence and word level noisy information in the matching process. Noisy sentences are usually easy to detect because previous work has shown that their similarity can be explicitly evaluated by the word overlapping, so we directly use PageRank to filter such information based on a sentence similarity graph. Unlike sentences, words rely on their contexts to express concrete meanings, so we propose to jointly learn the filtering and matching process, to well capture the critical word-level matching signals. Specifically, a word graph is first built based on the attention scores in each self-attention block of Transformer, and key words are then selected by applying PageRank on this graph. In this way, noisy words will be filtered out layer by layer in the matching process. Experimental results show that Match-Ignition outperforms both SOTA short text matching models and recent long-form text matching models. We also conduct detailed analysis to show that Match-Ignition efficiently captures important sentences and words, to facilitate the long-form text matching process. © 2021, CC BY.

关键词：

Reconstruction Algorithm of Heterogeneous network data Flow in Smart Factory Based on SDN 14

学校读者我要写书评

暂无评论

Reconstruction Algorithm of Heterogeneous Network Data Flow ...

14th International Conference on Measuring technology and Mechatronics Automation, ICMTMA 2022

作者： Chen, Yanping Peng, Jiajia Xia, Hong Wang, Zhongmin Gao, Cong Wang, Fengwei School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China ZTE Corporation No.55 Hi-techRoadSouth Shenzhen518057 China

ISBN: (纸本)9781665499781

In smart factories, the wide application of a variety of intelligent manufacturing devices and advanced sensors leads to the increasing demand for data exchange between different devices. In order to realize the flexible forwarding of multi-source manufacturing data in heterogeneous networks and the optimal utilization of network resources, in this article, we combined smartphone manufacturing scenarios, referred to the data flow reconstruction algorithm in related documents, analyzed the high dynamics of the data flow and proposed a data flow reconstruction algorithm based on routing-protocol, according to the particularity of different data forwarding and processing procedures, redesigned and defined the data flow in the scene. Finally, the results of Mininet simulation experiments showed that our proposed algorithm reduces the average transmission delay. © 2022 IEEE

关键词： Heterogeneous networks