检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Xiao, Liqiang Ma, Jun Dong, Xin Luna Martinez-Gomez, Pascual Zalmout, Nasser Zhang, Chenwei Zhao, Tong He, Hao Jin, Yaohui MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University *** Inc State Key Lab of Advanced Optical Communication System and Network Shanghai Jiao Tong University

Successful conversational search systems can present natural, adaptive and interactive shopping experience for online shopping customers. However, building such systems from scratch faces real word challenges from both imperfect product schema/knowledge and lack of training dialog data. In this work we first propose ConvSearch, an end-to-end conversational search system that deeply combines the dialog system with search. It leverages the text profile to retrieve products, which is more robust against imperfect product schema/knowledge compared with using product attributes alone. We then address the lack of data challenges by proposing an utterance transfer approach that generates dialogue utterances by using existing dialog from other domains, and leveraging the search behavior data from e-commerce retailer. With utterance transfer, we introduce a new conversational search dataset for online shopping. Experiments show that our utterance transfer method can significantly improve the availability of training dialogue data without crowd-sourcing, and the conversational search system significantly outperformed the best tested baseline. © 2021, CC BY-NC-SA.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Theoretical Analysis of Weakly-coupled Multicore Fibers’ Potentials in Subsea communications

Theoretical Analysis of Weakly-coupled Multicore Fibers’ Po...

引用

Asia communications and Photonics Conference and Exhibition (ACP)

作者： Lin Sun Gordon Ning Liu Yi Cai Gangxiang Shen Junwei Zhang Zhaohui Li Chao Lu Suzhou Key Laboratory of Advanced Optical Communication Network Technology School of Electronic and Information Engineering Soochow University Suzhou China Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems and State Key Laboratory of Optoelectronic Materials and Technologies School of Electronics and Information Technology Sun Yat-sen University Guangzhou China

optical subsea cables have special limitations of feed power and cable size. We theoretically analyze the advantages of weakly-coupled multi-core fibers in subsea scenarios over the SMFs ribbon solution.

关键词： optical losses Underwater cables optical fibers Multiplexing Integrated optics Multicore processing optical fiber cables

来源：评论

学校读者我要写书评

暂无评论

Federated Edge Learning via Integrated Sensing, Computation, and communication

Federated Edge Learning via Integrated Sensing, Computation,...

引用

IEEE International Conference on communications (ICC)

作者： Peixi Liu Guangxu Zhu Shuai Wang Miaowen Wen Wu Luo H. Vincent Poor Shuguang Cui State Key Laboratory of Advanced Optical Communication Systems and Networks Peking University Shenzhen Research Institute of Big Data Chinese Academy of Sciences Shenzhen Institute of Advanced Technology School of Electronic and Information Engineering South China University of Technology Department of Electrical and Computer Engineering Princeton University the Guangdong Provincial Key Laboratory of Future Networks of Intelligence School of Science and Engineering (SSE) Future Network of Intelligence Institute (FNii) the Chinese University of Hong Kong Shenzhen

Sensing, computation, and communication (SC 2 ) are highly coupled processes in federated edge learning (FEEL) and need to be jointly designed in a task-oriented manner for pursuing the best FEEL performance under the stringent resource constraints at edge devices. However, this remains an open problem as there is a lack of theoretical understanding on how the SC 2 resources jointly affect the FEEL performance. In this paper, we address the problem of joint SC 2 resource allocation for FEEL via a concrete case study of human motion recognition based on wireless sensing. Specifically, the joint SC 2 resource allocation problem is cast to maximize the convergence speed of FEEL, under the constraints on training time and energy supply of each edge device. Solving this problem entails solving two subproblems in order: the first one reduces to determining a joint sensing and communication resource allocation that maximizes the total number of samples sensed during the entire training process; the second one concerns the partition of the total number of sensed samples over communication rounds to determine the batch size at each round for convergence speed maximization. Finally, extensive simulation results are provided to validate the superiority of the proposed scheme over several baseline schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dependent multi-task learning with causal intervention for image captioning

arXiv

引用

arXiv 2021年

作者： Chen, Wenqing Tian, Jidong Fan, Caoyun He, Hao Jin, Yaohui MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China State Key Lab of Advanced Optical Communication System and Network Shanghai Jiao Tong University China

Recent work for image captioning mainly followed an extract-then-generate paradigm, pre-extracting a sequence of object-based features and then formulating image captioning as a single sequence-to-sequence task. Although promising, we observed two problems in generated captions: 1) content inconsistency where models would generate contradicting facts;2) not informative enough where models would miss parts of important information. From a causal perspective, the reason is that models have captured spurious statistical correlations between visual features and certain expressions (e.g., visual features of "long hair" and "woman"). In this paper, we propose a dependent multi-task learning framework with the causal intervention (DMTCI). Firstly, we involve an intermediate task, bag-of-categories generation, before the final task, image captioning. The intermediate task would help the model better understand the visual features and thus alleviate the content inconsistency problem. Secondly, we apply Pearl’s do-calculus on the model, cutting off the link between the visual features and possible confounders and thus letting models focus on the causal visual features. Specifically, the high-frequency concept set is considered as the proxy confounders where the real confounders are inferred in the continuous space. Finally, we use a multi-agent reinforcement learning (MARL) strategy to enable end-to-end training and reduce the inter-task error accumulations. The extensive experiments show that our model outperforms the baseline models and achieves competitive performance with state-of-the-art models. © 2021, CC BY.

关键词： Fertilizers

来源：评论

学校读者我要写书评

暂无评论

Modeling content importance for summarization with pre-trained language models

Modeling content importance for summarization with pre-train...

引用

2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020

作者： Xiao, Liqiang Wang, Lu He, Hao Jin, Yaohui MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China University of Michigan United States State Key Lab of Advanced Optical Communication System and Network Shanghai Jiao Tong University China

ISBN: (纸本)9781952148606

Modeling content importance is an essential yet challenging task for summarization. Previous work is mostly based on statistical methods that estimate word-level salience, which does not consider semantics and larger context when quantifying importance. It is thus hard for these methods to generalize to semantic units of longer text spans. In this work, we apply information theory on top of pre-trained language models and define the concept of importance from the perspective of information amount. It considers both the semantics and context when evaluating the importance of each semantic unit. With the help of pre-trained language models, it can easily generalize to different kinds of semantic units (n-grams or sentences). Experiments on CNN/Daily Mail and New York Times datasets demonstrate that our method can better model the importance of content than prior work based on F1 and ROUGE scores. © 2020 Association for Computational Linguistics

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Global Map Assisted Multi-Agent Collision Avoidance via Deep Reinforcement Learning around Complex Obstacles

Global Map Assisted Multi-Agent Collision Avoidance via Deep...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Yuanyuan Du Jianan Zhang Jie Xu Xiang Cheng Shuguang Cui Future Network of Intelligence Institute (FNii) School of Science and Engineering (SSE) The Chinese University of Hong Kong Shenzhen Shenzhen China The State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing P. R. China SSE FNii The Chinese University of Hong Kong Shenzhen Shenzhen China Peng Cheng Laboratory Shenzhen China

state-of-the-art multi-agent collision avoidance algorithms face limitations when applied to cluttered public environments, where obstacles may have a variety of shapes and structures. The issue arises because most of these algorithms are agent-level methods. They concentrate solely on preventing collisions between the agents while the obstacles are handled merely out-of-policy. Obstacle-aware policies output an action considering both agents and obstacles. Current obstacle-aware algorithms, mainly based on Lidar sensor data, struggle to handle collision avoidance around complex obstacles. To resolve this issue, this paper investigates how to find a better way to travel around diverse obstacles. In particular, we present a global map assisted collision avoidance algorithm which, following the lead of a high-level goal guide and using an obstacle representation called distance map, considers other agents and obstacles simultaneously. Moreover, our model can be loaded into each agent individually, making it applicable to large maps or more agents. Simulation results indicate that our model outperforms the state-of-the-art algorithms, showing in scenarios with complex obstacles. We present a notion for incorporating global information in decentralized decision-making, along with a method for extending agent-level algorithms to cluttered environments in real-world scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

$8\times 8$ Microring optical Switch on a Dual-layer Si3N4-on-SOI Platform

$8\times 8$ Microring Optical Switch on a Dual-layer Si3N4-o...

引用

Asia communications and Photonics Conference and Exhibition (ACP)

作者： Xin Li Wei Gao Liangjun Lu Jianping Chen Linjie Zhou State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Key Lab of Navigation and Location Services Shanghai Institute for Advanced Communication and Data Science Shanghai Jiao Tong University Shanghai China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu China

We demonstrate an $8\times 8$ microring switch based on a dual-layer Si3N4-on-SOI platform. Experimental results show the chip has a fiber-to- fiber insertion loss < 9.23 dB, crosstalk < -22.5 dB and optical b... 详细信息

ISBN: (纸本)9781665410953

关键词： optical fiber losses optical switches optical device fabrication Crosstalk Insertion loss Bandwidth optical crosstalk

来源：评论

学校读者我要写书评

暂无评论

Impact of Aperture Size on Beam Evolution of optical Phased Arrays

Impact of Aperture Size on Beam Evolution of Optical Phased ...

引用

optical Fiber communication (OFC) Conference

作者： Weihan Xu Chuxin Liu Yuyao Guo Xinhang Li Liangjun Lu Jianping Chen Linjie Zhou State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Key Lab of Navigation and Location Services Shanghai Institute for Advanced Communication and Data Science Shanghai Jiao Tong University Shanghai China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu China

We investigate the beam evolution of optical phased arrays. The model is validated with a 1-cm-long grating antenna and applied to both large-scale arrays and long antennas for its impact.

ISBN: (纸本)9781943580866

We investigate the beam evolution of optical phased arrays. The model is validated with a 1-cm-long grating antenna and applied to both large-scale arrays and long antennas for its impact.

关键词： Phased arrays optical fibers Integrated optics optical imaging Laser modes optical fiber communication Laser beams

来源：评论

学校读者我要写书评

暂无评论

A hybrid-integrated external cavity laser with ultra-wide wavelength tuning range and high side-mode suppression

A hybrid-integrated external cavity laser with ultra-wide wa...

引用

optical Fiber communication (OFC) Conference

作者： Yuyao Guo Xinhang Li Weihan Xu Chuxin Liu Minhui Jin Liangjun Lu Jingya Xie Anton Stroganov Jianping Chen Linjie Zhou State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Institute for Advanced Communication and Data Science Shanghai Jiao Tong University Shanghai China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu China Terahertz Technology Innovation Research Institute Terahertz Spectrum and Imaging Technology Cooperative Innovation Center Shanghai Key Lab of Modern Optical System University of Shanghai for Science and Technology Shanghai China LIGENTEC SA EPFL Innovation Park Bâtiment L Ecublens Switzerland

We present a III-V/Si 3 N 4 hybrid-integrated tunable laser. The laser shows a record of ~170-nm tuning range with a side mode suppression ratio above 64 dB and an intrinsic linewidth below 2.8 kHz. © 2022 The A... 详细信息

ISBN: (纸本)9781557524669

关键词： Performance evaluation Couplings Laser modes Optics optical fiber communication Broadband communication Laser tuning

来源：评论

学校读者我要写书评

暂无评论

Task-Oriented Over-the-Air Computation for Multi-Device Edge AI

arXiv

引用

arXiv 2022年

作者： Wen, Dingzhu Jiao, Xiang Liu, Peixi Zhu, Guangxu Shi, Yuanming Huang, Kaibin Network Intelligence Center School of Information Science and Technology ShanghaiTech University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University China Departement of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

Edge inference refers to the use of artificial intelligent (AI) models at the network edge to provide mobile devices inference services and thereby enable intelligent services such as auto-driving and Metaverse towards 6G. However, departing from the classic paradigm of data-centric designs, the 6G networks for supporting edge AI features task-oriented techniques that focus on effective and efficient execution of AI task. Targeting end-to-end system performance, such techniques are sophisticated as they aim to seamlessly integrate sensing (data acquisition), communication (data transmission), and computation (data processing). Aligned with the paradigm shift, a task-oriented over-the-air computation (AirComp) scheme is proposed in this paper for multi-device split-inference system. In the considered system, local feature vectors, which are extracted from the real-time noisy sensory data on devices, are aggregated over-the-air by exploiting the waveform superposition in a multiuser channel. Then the aggregated features as received at a server are fed into an inference model with the result used for decision making or control of actuators. To design inference-oriented AirComp, the transmit precoders at edge devices and receive beamforming at edge server are jointly optimized to rein in the aggregation error and maximize the inference accuracy. The problem is made tractable by measuring the inference accuracy using a surrogate metric called discriminant gain, which measures the discernibility of two object classes in the application of object/event classification. It is discovered that the conventional AirComp beamforming design for minimizing the mean square error in generic AirComp with respect to the noiseless case may not lead to the optimal classification accuracy. The reason is due to the overlooking of the fact that feature dimensions have different sensitivity towards aggregation errors and are thus of different importance levels for classification. This issue

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：