检索结果-内蒙古大学图书馆

58th Annual Meeting of the Association for Computational Linguistics, ACL 2020

作者： Karan, Mladen Vulić, Ivan Korhonen, Anna Glavaš, Goran TakeLab Faculty of Electrical Engineering and Computing University of Zagreb Language Technology Lab TAL University of Cambridge Data and Web Science Group University of Mannheim

ISBN: (纸本)9781952148255

Effective projection-based cross-lingual word embedding (CLWE) induction critically relies on the iterative self-learning procedure. It gradually expands the initial small seed dictionary to learn improved cross-lingual mappings. In this work, we present CLASSYMAP, a classification-based approach to self-learning, yielding a more robust and a more effective induction of projection-based CLWEs. Unlike prior self-learning methods, our approach allows for integration of diverse features into the iterative process. We show the benefits of CLASSYMAP for bilingual lexicon induction: we report consistent improvements in a weakly supervised setup (500 seed translation pairs) on a benchmark with 28 language pairs. © 2020 Association for Computational Linguistics

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Machine’s Statistical Parsing and Human’s Cognitive Preference for Garden Path Sentences 2nd

Machine’s Statistical Parsing and Human’s Cognitive Prefer...

引用

2nd International Conference on Human Interaction and Emerging Technologies: Future Applications, IHIET-AI 2020

作者： Du, Jiali Yu, Pingfang Li, Xinguang Lab of Language Engineering and Computing Guangzhou China Institute of Chinese Language and Culture Guangzhou China Center for Linguistics and Applied Linguistics Guangdong University of Foreign Studies Baiyun Avenue North 2 Guangzhou510420 China

ISBN: (纸本)9783030442668

We focus in this article on the comparison between machine statistical parsing and human cognitive preference when dealing with the semantic circuit of garden path sentences. Stanford parser and 126 Chinese college students are introduced to discuss the parsing of garden path sentences. Machine has the ability to successfully parse sentences based on statistical information. If the statistical result is coincident with answer, an excellent parsing result comes into being. Otherwise, ambiguous effect and processing breakdown may occur. Human beings have their cognitive preference. When they are required to parse garden path sentences, some are confused by ambiguity just as machine does. However, some people, mostly belonging to high span readers with more linguistic experience, have special ability to disambiguate the sentences after backtracking and reanalyzing. We draw a conclusion that human beings sometimes parse some types of sentences better than machine does. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Test-Time Training-Free Domain Adaptation

Test-Time Training-Free Domain Adaptation

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yongxiang Feng Weihua He Kaichao You Bing Liu Ziyang Zhang Yaoyuan Wang Minglei Li Yihang Lou Jiawei Li Guoqi Li Jianxing Liao Advanced Computing and Storage Lab Huawei Technologies Co. Ltd. School of Electronics Engineering and Computer Science Peking University China Language & Speech Innovation Lab Huawei Technologies Co. Ltd. GoTen AI Lab Department of Intelligent Vision Huawei Technologies Co. Ltd. China Department of Production Automation Development Huawei Technologies Co. Ltd. China Institute of Automation Chinese Academy of Sciences China

Deploying deep learning models to new environments is very challenging. Domain adaptation (DA) is a promising paradigm to solve the problem by collecting and adapting to unlabeled data in new environments. Though research efforts have led to steady performance improvement over the past decade, DA algorithms are still hard to deploy, as training on unlabeled new data makes tuning difficult and not feasible for inference-only devices. To make DA practical, in this paper we study a new problem named Test-time Training-Free Domain Adaptation (TTDA), where trained models must adapt to a single input (mimicking the test-time scenario) without training. By exploiting spatial activation that was previously overlooked and simply averaged out, we propose a simple method based on Feature Statistics Transformation (FST) on-the-fly for each test example. The proposed algorithm is tested in the TTDA setting on two standard DA benchmarks. Surprisingly, it surpasses or performs on par with state-of-the-art DA methods, even though they require additional training. We envision that this training-free paradigm has the potential to bring DA to embedded devices and would be of interest to audience of community.

关键词： Training Performance evaluation Adaptation models Transfer learning Signal processing algorithms Statistical distributions Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Combining deep generative models and multi-lingual pretraining for semi-supervised document classification

arXiv

引用

arXiv 2021年

作者： Zhu, Yi Shareghi, Ehsan Li, Yingzhen Reichart, Roi Korhonen, Anna Language Technology Lab University of Cambridge United Kingdom Department of Data Science & AI Monash University Australia Department of Computing Imperial College London United Kingdom Faculty of Industrial Engineering and Management Technion IIT

Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP. Nonetheless, their development has happened in isolation, while the combination of both could potentially be effective for tackling task-specific labelled data shortage. To bridge this gap, we combine semi-supervised deep generative models and multi-lingual pretraining to form a pipeline for document classification task. Compared to strong supervised learning baselines, our semi-supervised classification framework is highly competitive and outperforms the state-of-the-art counterparts in low-resource settings across several languages. Copyright © 2021, The Authors. All rights reserved.

关键词： Information retrieval systems

来源：评论

学校读者我要写书评

暂无评论

Closed-Loop Safe Correction for Reinforcement Learning Policy 1

引用

4th International Conference on Ubiquitous Security, UbiSec 2024

作者： Yi, Zhi Lv, Qi Chen, Shuhong Liang, Ying Dai, Yinglong Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Normal University Changsha410081 China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China Blockchain Innovation Lab Swinburne University of Technology MelbourneVIC3122 Australia Molecular Nutrition Branch National Engineering Research Center of Rice and By-product Deep Processing College of Food Science and Engineering Central South University of Forestry and Technology Hunan Changsha410004 China

ISBN: (数字)9789819648368

ISBN: (纸本)9789819648351

Trial and error learning is an approach with uncertain consequences. How to maintain policy security, stability, and efficiency under controlled circumstances, posing a significant academic challenge. Such as Reinforcement Learning (RL) leverages the neural network parameter space to identify the optimal solution for achieving the optimal mapping of the policy space. However, even a slight fluctuation in the parameter space can lead to policy collapse. To solve it, we propose a method called Closed-loop Safe Correction (CLSC). This method employs twin agents to establish a closed-loop framework for policy and sampling data distribution, gradually improving policy efficiency while ensuring policy safety. Base on theoretical and experimental analysis, CLSC elucidates the performance, influencing factors, and advantages of this approach in policy safety scenarios. These findings provide novel research insights and practical directions for advancing safe RL. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Node transfer with graph contrastive learning for class-imbalanced node classification

引用

Neural Networks 2025年 190卷 107674页

作者： Li, Yangding Zhao, Xiangchao Zeng, Yangyang Feng, Hao Chai, Jiawei Xie, Hao Fu, Shaobin Zhang, Shichao College of Information Science and Engineering Hunan Normal University Changsha China Hunan Provincial Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin China

In graph representation learning, the class imbalance problem is a significant challenge that has received much attention from academics. Although current approaches have shown promising results, they have not adequately addressed the problems of node quantity imbalance and feature space imbalance in datasets. This research presents a node transfer with graph contrastive learning framework (NT-GCL) that aims to improve the representation capabilities of graph neural networks for minority classes nodes by balancing node quantity and feature space distributions. First, the proposed node transfer algorithm redistributes misclassified nodes from majority classes to achieve a balanced distribution of node quantity and feature space. This approach effectively prevents the feature space of minority classes from being compressed by majority classes during information propagation, further mitigating potential imbalance issues. Subsequently, the self-supervised contrastive learning strategy is employed to train the model without relying on labels, reducing the bias introduced by labeled data. Experiments conducted with various encoders on six public datasets demonstrate that NT-GCL exhibits strong competitiveness in class-imbalanced node classification. © 2025 Elsevier Ltd

关键词： Class imbalance Graph contrastive learning Graph neural network Node classification Node transfer

来源：评论

学校读者我要写书评

暂无评论

Overview of the Tenth Dialog System Technology Challenge: DSTC10

引用

IEEE/ACM Transactions on Audio Speech and language Processing 2024年 32卷 765-778页

作者： Yoshino, Koichiro Chen, Yun-Nung Crook, Paul Kottur, Satwik Li, Jinchao Hedayatnia, Behnam Moon, Seungwhan Fei, Zhengcong Li, Zekang Zhang, Jinchao Feng, Yang Zhou, Jie Kim, Seokhwan Liu, Yang Jin, Di Papangelis, Alexandros Gopalakrishnan, Karthik Hakkani-Tur, Dilek Damavandi, Babak Geramifard, Alborz Hori, Chiori Shah, Ankit Zhang, Chen Li, Haizhou Sedoc, Joao D'haro, Luis F. Banchs, Rafael Rudnicky, Alexander Guardian Robot Project R-IH RIKEN 2-2-2 Hikaridai Seika Shoraku619-0288 Japan Information Science Nara Institute of Science and Technology Ikoma630-0101 Japan Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Inc. Palo AltoCA95054 United States Alexa AI *** Inc. SunnyvaleCA94089 United States Meta Seattle RedmondWA98052 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Tencent AI Lab Beijing Beijing China Kexueyuan South Road Zhongguancun Beijing100190 China Beijing 100190 China Alexa AI *** Inc. SunnyvaleCA United States 1120 Enterprise way Sunnyvale94089 United States *** Inc. SeattleWA United States Menlo Park CA United States Audio and Speech Group Mitsubishi Electric Research Laboratories CambridgeMA02139-1955 United States Carnegie Mellon University Department of Language and Information Technologies or just Carnegie Mellon University Pittsburgh United States National University of Singapore Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Shenzhen Research Institute of Big Data School of Data Science Chinese University of Hong Kong Shenzhen518172 China New York University New YorkNY United States ETSI de Telecomunicacion - Speech Technology and Machine Learning Group Universidad Politecnica de Madrid Ciudad Universitaria Madrid28040 Spain Nanyang Technological University Singapore Singapore Carnegie Mellon University PittsburghPA United States

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio Visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks. © 2023 The Authors.

关键词： Job analysis

来源：评论

学校读者我要写书评

暂无评论

Multidirectional associative optimization of function-specificword representations

arXiv

引用

arXiv 2020年

作者： Gerz, Daniela Vulic, Ivan Rei, Marek Reichart, Roi Korhonen, Anna Language Technology Lab University of Cambridge PolyAI Limited London United Kingdom Department of Computing Imperial College London Faculty of Industrial Engineering and Management Technion Iit

We present a neural framework for learning associations between interrelated groups of words such as the ones found in Subject-Verb-Object (SVO) structures. Our model induces a joint function-specific word vector space, where vectors of e.g. plausible SVO compositions lie close together. The model retains information about word group membership even in the joint space, and can thereby effectively be applied to a number of tasks reasoning over the SVO structure. We show the robustness and versatility of the proposed framework by reporting state-of-The-Art results on the tasks of estimating selectional preference and event similarity. The results indicate that the combinations of representations learned with our task-independent model outperform task-specific architectures from prior work, while reducing the number of parameters by up to 95%. Copyright © 2020, The Authors. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Robust Deep Learning Framework for Predicting Respiratory Anomalies and Diseases 42

Robust Deep Learning Framework for Predicting Respiratory An...

引用

42nd Annual International Conferences of the IEEE engineering in Medicine and Biology Society, EMBC 2020

作者： Pham, Lam McLoughlin, Ian Phan, Huy Tran, Minh Nguyen, Truc Palaniappan, Ramaswamy University of Kent School of Computing Medway Kent United Kingdom University of Science and Technology of China National Engineering Laboratory for Speech and Language Information Processing Hefei China Queen Mary University School of Electronic Engineering and Computer Science London United Kingdom University of Oxford Nuffield Department of Anaesthesia United Kingdom Graz University of Technology Signal Processing and Speech Communication Lab Austria

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119908

This paper presents a robust deep learning framework developed to detect respiratory diseases from recordings of respiratory sounds. The complete detection process firstly involves front end feature extraction where recordings are transformed into spectrograms that convey both spectral and temporal information. Then a back-end deep learning model classifies the features into classes of respiratory disease or anomaly. Experiments, conducted over the ICBHI benchmark dataset of respiratory sounds, evaluate the ability of the framework to classify sounds. Two main contributions are made in this paper. Firstly, we provide an extensive analysis of how factors such as respiratory cycle length, time resolution, and network architecture, affect final prediction accuracy. Secondly, a novel deep learning based framework is proposed for detection of respiratory diseases and shown to perform extremely well compared to state of the art methods. © 2020 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

The integration of artificial intelligence models to augment imaging modalities in pancreatic cancer

引用

Journal of Pancreatology 2020年第4期3卷 173-180页

作者： Xianze Wang Wen Yuan Chung Elon Correa Yi Zhu Eyad Issa Ashley R.Dennison Department of Surgery Peking Union Medical College HospitalChinese Academy of Medical Science&Peking Union Medical CollegeBeijingChina Department of Hepatobiliary and Pancreatic Surgery Leicester General HospitalLeicester School of Computing Science and EngineeringUniversity of SalfordManchester Language Technology Lab University of CambridgeCambridgeUK

Pancreatic ductal adenocarcinoma(PDAC)is an aggressive malignancy with a limited number of effective *** emerging technologies such as artificial intelligence(AI)to facilitate the earlier diagnosis and decision-making process represents one of the most promising areas for *** integration of AI models to augment imaging modalities in PDAC has made great progression in the past 5 years,especially in organ segmentation,AI-aided diagnosis,and radiomics based individualized *** this article,we review the developments of AI in the field of PDAC and the present clinical *** also examine the barriers to future development and more widespread application which will require increased familiarity of the underlying technology among clinicians to promote the necessary enthusiasm and collaboration with computer professionals.

关键词： Artificial intelligence Deep learning Imaging modality Machine learning Pancreatic ductal adenocarcinoma

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：