检索结果-内蒙古大学图书馆

Explicit contextual semantics for text comprehension 33

学校读者我要写书评

暂无评论

Explicit contextual semantics for text comprehension

33rd Pacific Asia Conference on Language, Information and Computation, PACLIC 2019

作者： Zhang, Zhuosheng Wu, Yuwei Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China College of Zhiyuan Shanghai Jiao Tong University China

Who did what to whom is a major focus in natural language understanding, which is right the aim of semantic role labeling (SRL) task. Despite of sharing a lot of processing characteristics and even task purpose, it is surprisingly that jointly considering these two related tasks was never formally reported in previous work. Thus this paper makes the first attempt to let SRL enhance text comprehension and inference through specifying verbal predicates and their corresponding semantic roles. In terms of deep learning models, our embeddings are enhanced by explicit contextual semantic role labels for more fine-grained semantics. We show that the salient labels can be conveniently added to existing models and significantly improve deep learning models in challenging text comprehension tasks. Extensive experiments on benchmark machine reading comprehension and inference datasets verify that the proposed semantic learning helps our system reach new state-of-the-art over strong baselines which have been enhanced by well pretrained language models from the latest progress. Copyright © 2019 Zhuosheng Zhang, Yuwei Wu, Zuchao Li and Hai Zhao.

关键词： Semantics

Graph Convolutional Networks for Temporal Action Localization

学校读者我要写书评

暂无评论

Graph Convolutional Networks for Temporal Action Localizatio...

International Conference on computer Vision (ICCV)

作者： Runhao Zeng Wenbing Huang Chuang Gan Mingkui Tan Yu Rong Peilin Zhao Junzhou Huang School of Software Engineering South China University of Technology China Tencent AI Lab Department of Computer Science and Technology Tsinghua University MIT-IBM Watson AI Lab Peng Cheng Laboratory Shenzhen

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Most state-of-the-art action localization systems process each action proposal individually, without explicitly exploiting their relations during learning. However, the relations between proposals actually play an important role in action localization, since a meaningful action always consists of multiple proposals in a video. In this paper, we propose to exploit the proposal-proposal relations using GraphConvolutional Networks (GCNs). First, we construct an action proposal graph, where each proposal is represented as a node and their relations between two proposals as an edge. Here, we use two types of relations, one for capturing the context information for each proposal and the other one for characterizing the correlations between distinct actions. Then we apply the GCNs over the graph to model the relations among different proposals and learn powerful representations for the action classification and localization. Experimental results show that our approach significantly outperforms the state-of-the-art on THUMOS14(49.1% versus 42.8%). Moreover, augmentation experiments on ActivityNet also verify the efficacy of modeling action proposal relationships.

关键词：

Customizing object detectors for indoor robots

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Alabachi, Saif Sukthankar, Gita Sukthankar, Rahul Department of Computer Engineering University of Central Florida OrlandoFL United States University of Technology Baghdad Iraq Department of Computer Science University of Central Florida OrlandoFL United States Google AI

Object detection models based on convolutional neural networks (CNNs) demonstrate impressive performance when trained on large-scale labeled datasets. While a generic object detector trained on such a dataset performs adequately in applications where the input data is similar to user photographs, the detector performs poorly on small objects, particularly ones with limited training data or imaged from uncommon viewpoints. Also, a specific room will have many objects that are missed by standard object detectors, frustrating a robot that continually operates in the same indoor environment. This paper describes a system for rapidly creating customized object detectors. Data is collected from a quadcopter that is teleoperated with an interactive interface. Once an object is selected, the quadcopter autonomously photographs the object from multiple viewpoints to collect data to train DUNet (Dense Upscaled Network), our proposed model for learning customized object detectors from scratch given limited data. Our experiments compare the performance of learning models from scratch with DUNet vs. fine tuning existing state of the art object detectors, both on our indoor robotics domain and on standard datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Object detection

Relative attributing propagation: Interpreting the comparative contributions of individual units in deep neural networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Nam, Woo-Jeoung Gur, Shir Choi, Jaesik Wolf, Lior Lee, Seong-Whan Department of Computer and Radio Communications Engineering Korea University Department of Artificial Intelligence Korea University School of Computer Science Tel Aviv University Facebook AI Research Graduate School of Artificial Intelligence KAIST

As Deep Neural Networks (DNNs) have demonstrated superhuman performance in a variety of fields, there is an increasing interest in understanding the complex internal mechanisms of DNNs. In this paper, we propose Relative Attributing Propagation (RAP), which decomposes the output predictions of DNNs with a new perspective of separating the relevant (positive) and irrelevant (negative) attributions according to the relative influence between the layers. The relevance of each neuron is identified with respect to its degree of contribution, separated into positive and negative, while preserving the conservation rule. Considering the relevance assigned to neurons in terms of relative priority, RAP allows each neuron to be assigned with a bi-polar importance score concerning the output: from highly relevant to highly irrelevant. Therefore, our method makes it possible to interpret DNNs with much clearer and attentive visualizations of the separated attributions than the conventional explaining methods. To verify that the attributions propagated by RAP correctly account for each meaning, we utilize the evaluation metrics: (i) Outside-inside relevance ratio, (ii) Segmentation mIOU and (iii) Region perturbation. In all experiments and metrics, we present a sizable gap in comparison to the existing literature. Our source code is available in https://***/wjNam/Relative Attributing Propagation. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

Room-Temperature Charge-to-Spin Conversion from Quasi-2D Electron Gas at SrTiO3-Based Interfaces

学校读者我要写书评

暂无评论

physica status solidi (RRL) – Rapid Research Letters 2023年第6期17卷

作者： Utkarsh Shashank Angshuman Deka Chen Ye Surbhi Gupta Rohit Medwal Rajdeep Singh Rawat Hironori Asada X. Renshaw Wang Yasuhiro Fukuma Department of Physics and Information Technology Faculty of Computer Science and System Engineering Kyushu Institute of Technology 680-4 Kawazu Iizuka 820-8502 Japan Birck Nanotechnology Center School of Electrical and Computer Engineering Purdue University West Lafayette IN 47907 USA School of Physical and Mathematical Sciences Nanyang Technological University 637616 Singapore Natural Sciences and Science Education National Institute of Education Nanyang Technological University 637616 Singapore Department of Physics Indian Institute of Technology Kanpur Kanpur 208016 India Graduate School of Sciences and Technology for Innovation Yamaguchi University 2-16-1 Tokiwadai Ube 755-8611 Japan School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore Research Center for Neuromorphic AI hardware Kyushu Institute of Technology Kitakyushu 808-0196 Japan

Emotion recognition using support vector machine and deep neural network 1

学校读者我要写书评

暂无评论

14th National Conference on Man-Machine Speech Communication, NCMMSC 2017

作者： Chen, Ruinian Zhou, Ying Qian, Yanmin SpeechLab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Tencent AI Lab Seattle United States

ISBN: (数字)9789811081118

ISBN: (纸本)9789811081101

Emotion recognition from voice has recently attracted considerable interest in the fields of human-machine communication. In this paper, we propose an emotion recognition system which is a combination of three subsystems. The first and second subsystems utilize support vector machines (SVM) and deep neural networks (DNN) respectively to classify the features directly. In the third subsystem, we utilize DNN to extract segment-level features from raw data and show that they are effective for speech emotion recognition. The extracted segment-level features are emotion state probability distribution. Then we construct utterance-level features from segment-level probability distributions. Finally, utterance-level features are fed into a SVM to identify the emotions for each utterance. The experimental results show that all the subsystems outperform the hidden markov model (HMM) baseline, and the combined system get the best performance on F-score. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

Cost-effective incentive allocation via structured counterfactual inference

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Lopez, Romain Li, Chenchen Yan, Xiang Xiong, Junwu Jordan, Michael I. Qi, Yuan Song, Le Department of Electrical Engineering and Computer Sciences University of California Berkeley United States AI Department Ant Financial Service Group Department of Computer Science Shanghai Jiao Tong University College of Computing Georgia Institute of Technology

We address a practical problem ubiquitous in modern marketing campaigns, in which a central agent tries to learn a policy for allocating strategic financial incentives to customers and observes only bandit feedback. In contrast to traditional policy optimization frameworks, we take into account the additional reward structure and budget constraints common in this setting, and develop a new two-step method for solving this constrained counterfactual policy optimization problem. Our method first casts the reward estimation problem as a domain adaptation problem with supplementary structure, and then subsequently uses the estimators for optimizing the policy with constraints. We also establish theoretical error bounds for our estimation procedure and we empirically show that the approach leads to significant improvement on both synthetic and real datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Marketing

Margin matters: Towards more discriminative deep neural network embeddings for speaker recognition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xiang, Xu Wang, Shuai Huang, Houjun Qian, Yanmin Yu, Kai MoE Key Lab of Artificial Intelligence SpeechLab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai AI Speech Co. Ltd

Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy loss with softmax. However, this kind of loss function does not explicitly encourage inter-class separability and intraclass compactness. As a result, the embeddings are not optimal for speaker recognition tasks. In this paper, to address this issue, three different margin based losses which not only separate classes but also demand a fixed margin between classes are introduced to deep speaker embedding learning. It could be demonstrated that the margin is the key to obtain more discriminative speaker embeddings. Experiments are conducted on two public text independent tasks: VoxCeleb1 and Speaker in The Wild (SITW). The proposed approach can achieve the state-ofthe- art performance, with 25% 30% equal error rate (EER) reduction on both tasks when compared to strong baselines using cross entropy loss with softmax, obtaining 2.238% EER on VoxCeleb1 test set and 2.761% EER on SITW core-core test set, respectively. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

LaSO: Label-set operations networks for multi-label few-shot learning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Alfassy, Amit Karlinsky, Leonid aides, Amit Shtok, Joseph Harary, Sivan Feris, Rogerio Giryes, Raja Bronstein, Alex M. IBM Research AI Haifa Israel School of Electrical Engineering Tel-Aviv University Tel-Aviv Israel Department of Computer Science Technion Haifa Israel

Example synthesis is one of the leading methods to tackle the problem of few-shot learning, where only a small number of samples per class are available. However, current synthesis approaches only address the scenario of a single category label per image. In this work, we propose a novel technique for synthesizing samples with multiple labels for the (yet unhandled) multi-label few-shot classification scenario. We propose to combine pairs of given examples in feature space, so that the resulting synthesized feature vectors will correspond to examples whose label sets are obtained through certain set operations on the label sets of the corresponding input pairs. Thus, our method is capable of producing a sample containing the intersection, union or set-difference of labels present in two input samples. As we show, these set operations generalize to labels unseen during training. This enables performing augmentation on examples of novel categories, thus, facilitating multi-label few-shot classifier learning. We conduct numerous experiments showing promising results for the label-set manipulation capabilities of the proposed approach, both directly (using the classification and retrieval metrics), and in the context of performing data augmentation for multi-label few-shot learning. We propose a benchmark for this new and challenging task and show that our method compares favorably to all the common baselines. Our code will be made available upon acceptance. Copyright © 2019, The Authors. All rights reserved.

关键词： Vector spaces