Search Results for author:
Found 19 papers, 2 papers with code
基于话头话体共享结构信息的机器阅读理解研究(Rearch on Machine reading comprehension based on shared structure information between Naming and Telling)
“机器阅读理解(Machine Reading Comprehension, MRC)任务旨在让机器回答给定上下文的问题来测试机器理解自然语言的能力。目前, 基于大规模预训练语言模型的神经机器阅读理解模型已经取得重要进展, 但在涉及答案要素、线索要素和问题要素跨标点句、远距离关联时, 答案抽取的准确率还有待提升。本文通过篇章内话头话体结构分析, 建立标点句间远距离关联关系、补全共享缺失成分, 辅助机器阅读理解答案抽取;设计和实现融合话头话体结构信息的机器阅读理解模型, 在公开数据集CMRC2018上的实验结果表明, 模型的F1值相对于基线模型提升2. 4%, EM值提升6%。”
基于神经网络的半监督CRF中文分词(Semi-supervised CRF Chinese Word Segmentation based on Neural Network)
“分词是中文信息处理的基础任务之一。目前全监督中文分词技术已相对成熟并在通用领域取得较好效果, 但全监督方法存在依赖大规模标注语料且领域迁移能力差的问题, 特别是跨领域未登录词识别性能不佳。为缓解上述问题, 本文提出了一种充分利用相对易得的目标领域无标注文本、实现跨领域迁移的半监督中文分词框架;并设计实现了基于词记忆网络和序列条件熵的半监督权杒杆中文分词模型。实验结果表明本该模型在多个领域数据集上杆札值和杒杏杏杖值分别取得最高朲. 朳朵朥和朱朲. 朱朲朥的提升, 并在多个数据集上成为当前好结果。”
Generic Knowledge Boosted Pre-training For Remote Sensing Images
Deep learning models are essential for scene classification, change detection, land cover segmentation, and other remote sensing image understanding tasks.
Predicting Continuous Locomotion Modes via Multidimensional Feature Learning from sEMG
This term refers to the duration during which consistent and accurate predictions of mode transitions are made, measured from the time of the fifth correct prediction to the occurrence of the critical event leading to the task transition.
Context-Enhanced Detector For Building Detection From Remote Sensing Images
Our approach utilizes a three-stage cascade structure to enhance the extraction of contextual information and improve building detection accuracy.
CtxMIM: Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding
To address these problems, we propose a context-enhanced masked image modeling method (CtxMIM), a simple yet efficient MIM-based self-supervised learning for remote sensing image understanding.
HiT: Building Mapping with Hierarchical Transformers
The polygon head formulates a building polygon as serialized vertices with the bidirectional characteristic, a simple and elegant polygon representation avoiding the start or end vertex hypothesis.
Gait Cycle-Inspired Learning Strategy for Continuous Prediction of Knee Joint Trajectory from sEMG
This paper proposes a model integrating two gait cycle-inspired learning strategies to mitigate the challenge for predicting human knee joint trajectory.
Close-range Human Following Control on a Cane-type Robot with Multi-camera Fusion
Moreover, the cane robot can effectively adapt to a wide range of individual gait patterns and achieve stable human following at daily walking speeds (0. 75 m/s - 1. 45 m/s).
BiSVP: Building Footprint Extraction via Bidirectional Serialized Vertex Prediction
Extracting building footprints from remote sensing images has been attracting extensive attention recently.
IMU Data Processing For Inertial Aided Navigation: A Recurrent Neural Network Based Approach
In this work, we propose a novel method for performing inertial aided navigation, by using deep neural networks (DNNs).
Semi-supervised Hyperspectral Image Classification with Graph Clustering Convolutional Networks
To further lift the classification performance, in this work we propose a graph convolution network (GCN) based framework for HSI classification that uses two clustering operations to better exploit multi-hop node correlations and also effectively reduce graph size.
A Novel Transformation Approach of Shared-link Coded Caching Schemes for Multiaccess Networks
Applying the transformation approach to the well-known shared-link coded caching scheme proposed by Maddah-Ali and Niesen, we obtain a new multiaccess coded caching scheme that achieves the same load as the scheme of Hachem et al. but for any system parameters.
Information Theory Information Theory
Lifelong Property Price Prediction: A Case Study for the Toronto Real Estate Market
As a departure from prior work, Luce organizes the house data in a heterogeneous information network (HIN) where graph nodes are house entities and attributes that are important for house price valuation.
Visual-Inertial Localization for Skid-Steering Robots with Kinematic Constraints
While visual localization or SLAM has witnessed great progress in past decades, when deploying it on a mobile robot in practice, few works have explicitly considered the kinematic (or dynamic) constraints of the real robotic system when designing state estimators.
Pose Estimation for Ground Robots: On Manifold Representation, Integration, Re-Parameterization, and Optimization
In this paper, we focus on motion estimation dedicated for non-holonomic ground robots, by probabilistically fusing measurements from the wheel odometer and exteroceptive sensors.
A lossless data hiding scheme in JPEG images with segment coding
In this paper, we propose a lossless data hiding scheme in JPEG images.
Multi-view Laplacian Eigenmaps Based on Bag-of-Neighbors For RGBD Human Emotion Recognition
As RGB view and depth view lie in different spaces, a new distance metric bag of neighbors (BON) used in MvLE can get the similar distributions of the two views.
