检索结果-内蒙古大学图书馆

Asia-Pacific Conference on Software engineering

作者： Changxin Liu Ling Xu Wenhan Mu Rui Qin Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education China School of Big Data and Software Engineering Chongqing University Chongqing China

ISBN: (数字)9798331534011

ISBN: (纸本)9798331534028

Automated API recommendation technology can help developers quickly find target APIs that meet their require-ments. Some retrieval-based API recommendation approaches, such as BIKER and CLEAR, adopt an indirect API recommen-dation strategy. Although these approaches have shown good performance, we observed two limitations in these approaches: (1) These approaches heavily relies on the coverage of the collected question titles proposed by developers; (2) These approaches ignore the API source code information. To overcome the two limitations, we propose an approach named AnsAPIRec (Answer- directed API Recommendation), which leverages a pre-trained model and joint-attention mechanism in this paper. In addition to the fully qualified name of the API, AnsAPIRec extracts the corresponding source code from the JDK as an additional feature. AnsAPIRec adopts a direct API recommendation strategy, which directly calculates the similarity between user queries and API features, i.e., API fully qualified name and API source code, to find the target API, alleviating the reliance on question titles. To further enhance AnsAPIRec's ability to understand the semantics of the inputs, we propose a joint-attention mechanism to learn the interdependent representations between the queries and API features. This deep semantic fusion mechanism enables AnsAPIRec to perform well in understanding user intent and API functionality. We reused the APIBench-Q dataset, containing 5885 queries for training and 653 queries for testing. The experimental result shows that AnsAPIRec achieved an MRR of 0.473, significantly outperforming the baseline approaches, BIKER and CLEAR.

关键词： Training Source coding Semantics Feature extraction Testing Software engineering

来源：评论

学校读者我要写书评

暂无评论

MECNet: Multi-Scale Exposure-Consistency Learning via Fourier Transform for Exposure Correction

MECNet: Multi-Scale Exposure-Consistency Learning via Fourie...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Gaofei Qiao Zhibin Zhang Liqiang He Key Laboratory of Wireless Networks and Mobile Computing Engineering Research Center of Ecological Big Data Ministry of Education Inner Mongolia University Hohhot China Geomechanica Inc Canada

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In the real world, due to various challenging lighting conditions such as low light, underexposure, and overexposure, captured images often exhibit undesirable appearances. Given that images with different exposure levels require different correction processes, a single neural network struggles to produce satisfactory results. We propose a coarse-to-fine exposure correction model for learning exposure consistency representation to address underexposure and overexposure issues. Building upon the bilateral activation mechanism, we introduce the Fourier transform to capture global information and fuse it with locally extracted information through convolution to achieve superior feature representation. Additionally, we employ Laplacian pyramids to decompose the source image into different spatial frequency bands, then the image details are enhanced by denoising high-frequency layers. Experimental results on the MSEC and SICE datasets demonstrate the superiority of our proposed method over current state-of-the-art approaches. Our code will be made available on GitHub.

关键词： Representation learning Laplace equations Fourier transforms Image color analysis Plants (biology) Noise reduction Neural networks Lighting Feature extraction Software development management

来源：评论

学校读者我要写书评

暂无评论

RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL

arXiv

引用

arXiv 2023年

作者： Li, Haoyang Zhang, Jing Li, Cuiping Chen, Hong Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University of China China Engineering Research Center of Ministry of Education on Database and BI China Information School Renmin University of China China

One of the recent best attempts at Text-to-SQL is the pre-trained language model. Due to the structural property of the SQL queries, the seq2seq model takes the responsibility of parsing both the schema items (i.e., tables and columns) and the skeleton (i.e., SQL keywords). Such coupled targets increase the difficulty of parsing the correct SQL queries especially when they involve many schema items and logic operators. This paper proposes a ranking-enhanced encoding and skeleton-aware decoding framework to decouple the schema linking and the skeleton parsing. Specifically, for a seq2seq encoder-decode model, its encoder is injected by the most relevant schema items instead of the whole unordered ones, which could alleviate the schema linking effort during SQL parsing, and its decoder first generates the skeleton and then the actual SQL query, which could implicitly constrain the SQL parsing. We evaluate our proposed framework on Spider and its three robustness variants: Spider-DK, Spider-Syn, and Spider-Realistic. The experimental results show that our framework delivers promising performance and robustness. Our code is available at https://***/RUCKBReasoning/RESDSQL. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

LSBert: Lexical Simplification Based on BERT

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2021年 29卷 3064-3076页

作者： Qiang, Jipeng Li, Yun Zhu, Yi Yuan, Yunhao Shi, Yang Wu, Xindong Department of Computer Science Jiangsu Yangzhou China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Anhui Hefei China Mininglamp Academy of Sciences Minininglamp Beijing 100864 China

Lexical simplification (LS) aims at replacing complex words with simpler alternatives. LS commonly consists of three main steps: complex word identification, substitute generation, and substitute ranking. Existing LS methods focus on the contextual information of the complex word in the last step (substitute ranking). However, they miss out the following two facts: (1) The word complexity of a polysemous word is very closely related to its context;(2) The step of substitute generation regardless of the context will inevitably produce a large number of spurious candidates. Therefore, we propose a novel LS system LSBert based on pretrained language model BERT to address the aforementioned issues, which is capable of making use of the wider context when both identifying the words in need of simplification and generating substitute candidates for the complex words. Specifically, LSBert consists of a network for complex word identification by fine-tuning BERT and a network for substitute generation based on BERT. Experimental results show that LSBert performs well in both complex word identification and substitute generation, achieving state-of-the-art results in three benchmarks. © 2014 IEEE.

关键词： BERT Complex word identification Lexical simplification Sentence simplification

来源：评论

学校读者我要写书评

暂无评论

Switchable Online knowledge Distillation

arXiv

引用

arXiv 2022年

作者： Qian, Biao Wang, Yang Yin, Hongzhi Hong, Richang Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology China The University of Queensland

Online knowledge Distillation (OKD) improves the involved models by reciprocally exploiting the difference between teacher and student. Several crucial bottlenecks over the gap between them — e.g., Why and when does a large gap harm the performance, especially for student? How to quantify the gap between teacher and student? — have received limited formal study. In this paper, we propose Switchable Online knowledge Distillation (SwitOKD), to answer these questions. Instead of focusing on the accuracy gap at test phase by the existing arts, the core idea of SwitOKD is to adaptively calibrate the gap at training phase, namely distillation gap, via a switching strategy between two modes — expert mode (pause the teacher while keep the student learning) and learning mode (restart the teacher). To possess an appropriate distillation gap, we further devise an adaptive switching threshold, which provides a formal criterion as to when to switch to learning mode or expert mode, and thus improves the student’s performance. Meanwhile, the teacher benefits from our adaptive switching threshold and keeps basically on a par with other online arts. We further extend SwitOKD to multiple networks with two basis topologies. Finally, extensive experiments and analysis validate the merits of SwitOKD for classification over the state-of-the-arts. Our code is available at https://***/hfutqian/SwitOKD. Copyright © 2022, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

IKGN: Intention-aware knowledge Graph Network for POI Recommendation

IKGN: Intention-aware Knowledge Graph Network for POI Recomm...

引用

IEEE International Conference on data Mining (ICDM)

作者： Xiaoyu Zhu Chenyang Bu Bingbing Dong Shengwei Ji Yi He Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology China School of Artificial Intelligence and Big Data Hefei University China Department of Computer Science Old Dominion University USA Research Center for Knowledge Engineering Zhejiang Lab China

Point-of-Interest (POI) recommendation, pivotal for guiding users to their next interested locale, grapples with the persistent challenge of data sparsity. Whereas knowledge graphs (KGs) have emerged as a favored tool to mitigate the issue, existing KG-based methods tend to overlook two crucial elements: the intention steering users’ location choices and the high-order topological structure within the KG. In this paper, we craft an Intention-aware knowledge Graph (IKG) that harmonizes users’ visit histories, movement trajectories, and location categories to model user intentions. Building upon IKG, our novel Intention-aware knowledge Graph Network (IKGN) delves deeper into the POI recommendation by weighing and propagating node embeddings through an attention mechanism, capturing the unique locational intent of each user. A sequential model like GRU is then employed to ensure a comprehensive representation of users’ short- and long-term location preferences. An empirical study on two real-world datasets validates the effectiveness of our proposed IKGN, with it markedly outshining seven benchmark rival models in both Recall and NDCG metrics. The code of IKGN is available at https://***/Jungle123456/IKGN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2025年

作者： Li, Yangning Kang, Hui Li, Jiahui Sun, Geng Sun, Zemin Wang, Jiacheng Zhao, Changyuan Niyato, Dusit College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University 639798 Singapore College of Computing and Data Science Nanyang Technological University Singapore

An expansion of Internet of Things (IoTs) has led to significant challenges in wireless data harvesting, dissemination, and energy management due to the massive volumes of data generated by IoT devices. These challenges are exacerbated by data redundancy arising from spatial and temporal correlations. To address these issues, this paper proposes a novel data-driven collaborative beamforming (CB)-based communication framework for IoT networks. Specifically, the framework integrates CB with an overlap-based multi-hop routing protocol (OMRP) to enhance data transmission efficiency while mitigating energy consumption and addressing hot spot issues in remotely deployed IoT networks. Based on the data aggregation to a specific node by OMRP, we formulate a node selection problem for the CB stage, with the objective of optimizing uplink transmission energy consumption. Given the complexity of the problem, we introduce a softmax-based proximal policy optimization with long-short-term memory (SoftPPO-LSTM) algorithm to intelligently select CB nodes for improving transmission efficiency. Simulation results show that the proposed OMRP improves network lifetime by 17% compared to benchmark routing protocols, while the SoftPPO-LSTM method for CB node selection achieves an 8.3% increase in throughput over benchmark algorithms. The results also reveal that the combined OMRP with the SoftPPO- Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension 39

Hierarchical Alignment-enhanced Adaptive Grounding Network f...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Yaxian Ding, Henghui He, Shuting Jiang, Xudong Wei, Bifan Liu, Jun School of Computer Science and Technology Xi'an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University China Institute of Big Data Fudan University China Shanghai University of Finance and Economics China Nanyang Technological University Singapore School of Continuing Education Xi'an Jiaotong University China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University China

ISBN: (纸本)157735897X

In this work, we address the challenging task of Generalized Referring Expression Comprehension (GREC). Compared to the classic Referring Expression Comprehension (REC) that focuses on single-target expressions, GREC extends the scope to a more practical setting by further encompassing no-target and multi-target expressions. Existing REC methods face challenges in handling the complex cases encountered in GREC, primarily due to their fixed output and limitations in multi-modal representations. To address these issues, we propose a Hierarchical Alignment-enhanced Adaptive Grounding Network (HieA2G) for GREC, which can flexibly deal with various types of referring expressions. First, a Hierarchical Multi-modal Semantic Alignment (HMSA) module is proposed to incorporate three levels of alignments, including word-object, phrase-object, and text-image alignment. It enables hierarchical cross-modal interactions across multiple levels to achieve comprehensive and robust multi-modal understanding, greatly enhancing grounding ability for complex cases. Then, to address the varying number of target objects in GREC, we introduce an Adaptive Grounding Counter (AGC) to dynamically determine the number of output targets. Additionally, an auxiliary contrastive loss is employed in AGC to enhance object-counting ability by pulling in multi-modal features with the same counting and pushing away those with different counting. Extensive experimental results show that HieA2G achieves new state-of-the-art performance on the challenging GREC task and also the other 4 tasks, including REC, Phrase Grounding, Referring Expression Segmentation (RES), and Generalized Referring Expression Segmentation (GRES), demonstrating the remarkable superiority and generalizability of the proposed HieA2G. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Plus ça change, plus c'est la même chose – The Australian Records Management Case 18th

Plus ça change, plus c'est la même chose – The Australian...

引用

18th International Conference on Information for a Better World: Normality, Virtuality, Physicality, Inclusivity, iConference 2023

作者： Xie, Sherry L. Gao, Yubao Ma, Linqing School of Information Resource Management Renmin University of China Beijing100872 China Center for Digital Records Management Research Renmin University of China Beijing100872 China Key Laboratory of Data Engineering and Data Knowledge of the Ministry of Education of China Beijing100872 China Center for Archival Undertakings Renmin University of China Beijing100872 China

ISBN: (纸本)9783031280344

Intrigued by the information management replacing records management phenomenon, this study aimed at shedding light on it. Relying on preserved websites, the study examined relevant contents from 2007 to early 2022. It discovered the battle between records and information, and later on information asset. This battle incurred dazzling changes in managerial considerations, yet the challenges to management – either towards records, information, information and records, or information asset – remained the same. So were the unsatisfactory outcomes. A case seemed perfect to tell the plus ça change, plus c'est la même chose story. It is our hope that future studies can gather mighty strengthen and thus settle down the records-information battle once for all. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

MC-PDARTS: Multi-Cell Progressive Differentiable Architecture Search

MC-PDARTS: Multi-Cell Progressive Differentiable Architectur...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Qun Liu Yi Cai Junying Chen School of Software Engineering South China University of Technology Key Laboratory of Big Data and Intelligent Robot (SCUT) Ministry of Education Guangzhou China

Recently, network architecture search has been practiced in more and more tasks, but its high cost makes it difficult for small research teams or individual researchers to follow. Differentiable architecture search (DARTS) algorithm provides an easier available solution in searching effective network architectures. Although DARTS algorithm has greatly reduced the search cost as compared with other evolution based or reinforcement learning based methods, there is still a long way to go before it is widely used, since gradient based methods consume a lot of GPU memory and its search space lacks diversity. Encouraged by the idea of progressive differentiable architecture search (P-DARTS), we propose a multi-cell progressive differentiable architecture search (MC-PDARTS) algorithm, which allows cells at different levels to learn different structures, and progressively searches the best structure for the corresponding level in each search stage. The proposed algorithm greatly enlarges the search space of the search network while reducing the memory consumption and search time in the search process, and alleviates the problem of performance collapse caused by too many skip connections which often occur in previous gradient based methods. Compared with the previous algorithms, the proposed MC-PDARTS algorithm achieves state-of-the-art performance on CIFAR-10 and CIFAR-100 datasets with around 4-hour search on a single Nvidia GTX1080Ti GPU. In order to reduce the performance loss in the transfer process, MC-PDARTS searches directly on a large target dataset (ImageNet) without proxy tasks, achieving state-of-the-art performance.

关键词：

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：