检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Li, Jicun Li, Xingjian Wang, Tianyang Wang, Shi Cao, Yanan Xu, Chengzhong Dou, Dejing Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Big Data Lab Baidu Research China University of Alabama Birmingham United States Institute of Information Engineering Chinese Academy of Sciences China State Key Lab of Iotsc University of Macau China

ISBN: (纸本)9781728163277

Fine-tuning pre-trained language models, such as BERT, has shown enormous success among various NLP tasks. Though simple and effective, the process of fine-tuning has been found unstable, which often leads to unexpected poor performance. To increase stability and generalizability, most existing works resort to maintaining the parameters or representations of pre-trained models during fine-tuning. Nevertheless, very little work explores mining the reliable part of pre-learned information that can help to stabilize fine-tuning. To address this challenge, we introduce a novel solution in which we fine-tune BERT with stabilized cross-layer mutual information. Our method aims to preserve the reliable behaviors of cross-layer information propagation, instead of preserving the information itself, of the pre-trained model. Therefore, our method circumvents the domain conflicts between pre-trained and target tasks. We conduct extensive experiments with popular pre-trained BERT variants on NLP datasets, demonstrating the universal effectiveness and robustness of our method. © 2023 IEEE.

关键词： Fine-tuning Stability Mutual information Pre-trained Language Model

来源：评论

学校读者我要写书评

暂无评论

Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs

Context-Driven Index Trimming: A Data Quality Perspective to...

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Ma, Kexin Jin, Ruochun Wang, Haotian Wang, Xi Chen, Huan Tang, Yuhua Wang, Qian Institute for Quantum Information State Key Laboratory of High Performance Computing China College of Computer Science and Technology National University of Defense Technology Changsha China Intelligent Game and Decision Lab Academy of Military Science Beijing China

ISBN: (纸本)9798891761681

Retrieval-Augmented Large Language Models (RALMs) have made significant strides in enhancing the accuracy of generated responses. However, existing research often overlooks the data quality issues within retrieval results, often caused by inaccurate existing vector-distance-based retrieval methods. We propose to boost the precision of RALMs' answers from a data quality perspective through the Context-Driven Index Trimming (CDIT) framework, where Context Matching Dependencies (CMDs) are employed as logical data quality rules to capture and regulate the consistency between retrieved contexts. Based on the semantic comprehension capabilities of Large Language Models (LLMs), CDIT can effectively identify and discard retrieval results that are inconsistent with the query context and further modify indexes in the database, thereby improving answer quality. Experiments demonstrate average improvement of 3.75% in accuracy on challenging question-answering tasks. Also, the flexibility of CDIT is verified through its compatibility with various language models and indexing methods, which offers a promising approach to bolster RALMs' data quality and retrieval precision jointly. © 2024 Association for Computational Linguistics.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Monotonic and nonmonotonic gentzen deduction systems for L_(3)-valued propositional logic

引用

Frontiers of Computer Science 2021年第3期15卷 123-135页

作者： Cungen CAO Lanxi HU Yuefei SUI Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China

A sequent is a pair(Г,△),which is true under an as-signment if either some formula inГis false,or some formula in △ is *** L3-valued propositional logic,a mulisequent is a triple △|Θ|Г,which is true under an assignment if either some formula in △ has truth-value t,or some formula in Θ has truth-value m,or some formula in Г has truth-value￡.Corre-spondingly there is a sound and complete Gentzen deduction system G for multisequents which is ***,a CO-multisequent is a triple △:Θ:Г,which is valid if there is an assignment v in which each formula in△has truth-value≠t,each formula in Θ has truth-value≠m,and each formula in Г has truth-value≠￡.Correspondingly there is a sound and com-plete Gentzen deduction system G-for co-multisequents which is nonmonotonic.

关键词： three-valued logic multisequent co-multise-quent monotonicity Gentzen deduction system

来源：评论

学校读者我要写书评

暂无评论

Leveraging Slot-Aware Enhancements for Improved Zero-Shot Dialogue State Tracking

Leveraging Slot-Aware Enhancements for Improved Zero-Shot Di...

引用

Frontiers technology of information and Computer (ICFTIC), IEEE International Conference on

作者： Tianhang Song Haolei Hu Xinxin Chen Kangli Zi Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Beijing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Task-oriented dialogue systems (TOD) aim to help users complete specific tasks through multiple rounds of dialogue, in which Dialogue State Tracking (DST) is a key component. The training of DST models typically necessitates the availability of a substantial corpus of dialogue data with turn-level annotations. However, the collection of such data is both costly and inefficient. Despite the impressive performance of systems based on advanced large language models (LLMs), their closed-source nature restricts the potential for local deployment. To address this challenge, this paper proposes a new zero-shot slot-aware enhanced model (SAE), which introduces a novel coded prompting framework to enhance the DST capability of small parameter models in new domains and task scenarios. In particular, we have devised a prompting framework that employs code to refine task instructions. Furthermore, we have proposed a slot-aware question generation mechanism that generates slot-aware questions based on contextual details in accordance with the dialogue context, thereby enhancing the model's perception and matching capabilities for slots. In order to verify the effectiveness of the model, we conducted experiments on the MultiWOZ dataset. The results show that the SAE model has achieved significant performance improvements in zero-shot DST tasks.

关键词： Training Adaptation models Codes Large language models Computational modeling Termination of employment Predictive models Question generation Data models Context modeling

来源：评论

学校读者我要写书评

暂无评论

Combat data shift in few-shot learning with knowledge graph

引用

Frontiers of Computer Science 2023年第1期17卷 101-111页

作者： Yongchun ZHU Fuzhen ZHUANG Xiangliang ZHANG Zhiyuan QI Zhiping SHI Juan CAO Qing HE Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Institute of Artificial Intelligence Beihang UniversityBeijing 100191China Xiamen Institute of Data Intelligence Xiamen 361021China Computer Science and Engineering University of Notre DameIN 46556USA University of California San Diego La JollaCA 92093USA College of Information Engineering&Academy for Multidisciplinary Studies Capital Normal UniversityBeijing 100089China

Many few-shot learning approaches have been designed under the meta-learning framework, which learns from a variety of learning tasks and generalizes to new tasks. These meta-learning approaches achieve the expected performance in the scenario where all samples are drawn from the same distributions (i.i.d. observations). However, in real-world applications, few-shot learning paradigm often suffers from data shift, i.e., samples in different tasks, even in the same task, could be drawn from various data distributions. Most existing few-shot learning approaches are not designed with the consideration of data shift, and thus show downgraded performance when data distribution shifts. However, it is non-trivial to address the data shift problem in few-shot learning, due to the limited number of labeled samples in each task. Targeting at addressing this problem, we propose a novel metric-based meta-learning framework to extract task-specific representations and task-shared representations with the help of knowledge graph. The data shift within/between tasks can thus be combated by the combination of task-shared and task-specific representations. The proposed model is evaluated on popular benchmarks and two constructed new challenging datasets. The evaluation results demonstrate its remarkable performance.

关键词： few-shot data shift knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Enhanced Semantic Head for Cascade Instance Segmentation

Enhanced Semantic Head for Cascade Instance Segmentation

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Huang, Xuerong Su, Li Li, Guorong Zhang, Xinfeng Qing, Laiyun Huang, Qingming University of Chinese Academy of Sciences Beijing China Cas Key Lab of Big Data Mining and Knowledge Management Beijing China Institute of Computing Technology Cas Key Lab of Intelligent Information Processing Beijing China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Recently, cascade instance segmentation inspired by cascade object detection has achieved notable performance. Due to the lack of global information, many methods suffer from incomplete segmentation such as missing edge regions and discontinuities within instances. To solve this problem, we proposed an effective and flexible semantic head to extract enhanced spatial context information. A vision transformer is utilized to generate global context features, and a convolution network is adopted to generate spatial context features. After combining the two modules, we obtain enhanced semantic segmentation features for segmentation. Extensive experiments show that the enhanced semantic head achieves 40.6% and 42.3% mask AP for cascade predictor HTC and DSC, which surpass about 0.9 and 1.4 percentage points respectively. The enhanced semantic head is universal and effective to improve the performance of different cascade predictors. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection 41

ESNet: Evolution and Succession Network for High-Resolution ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Hongyu Cong, Runmin Li, Hua Xu, Qianqian Huang, Qingming Zhang, Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature;the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24. Copyright 2024 by the author(s)

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

Integrating Conjugate Gradients Into Evolutionary Algorithms for Large-Scale Continuous Multi-Objective Optimization

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1801-1817页

作者： Ye Tian Haowen Chen Haiping Ma Xingyi Zhang Kay Chen Tan Yaochu Jin the Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China the Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230601China IEEE the Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial IntelligenceAnhui UniversityHefei 230601China the Department of Computing The Hong Kong Polytechnic UniversityHong Kong SARChina the Faculty of Technology Bielefeld UniversityBielefeld 33619Germany

Large-scale multi-objective optimization problems(LSMOPs)pose challenges to existing optimizers since a set of well-converged and diverse solutions should be found in huge search *** evolutionary algorithms are good at solving small-scale multi-objective optimization problems,they are criticized for low efficiency in converging to the optimums of *** contrast,mathematical programming methods offer fast convergence speed on large-scale single-objective optimization problems,but they have difficulties in finding diverse solutions for ***,how to integrate evolutionary algorithms with mathematical programming methods to solve LSMOPs remains *** this paper,a hybrid algorithm is tailored for LSMOPs by coupling differential evolution and a conjugate gradient *** the one hand,conjugate gradients and differential evolution are used to update different decision variables of a set of solutions,where the former drives the solutions to quickly converge towards the Pareto front and the latter promotes the diversity of the solutions to cover the whole Pareto *** the other hand,objective decomposition strategy of evolutionary multi-objective optimization is used to differentiate the conjugate gradients of solutions,and the line search strategy of mathematical programming is used to ensure the higher quality of each offspring than its *** comparison with state-of-the-art evolutionary algorithms,mathematical programming methods,and hybrid algorithms,the proposed algorithm exhibits better convergence and diversity performance on a variety of benchmark and real-world LSMOPs.

关键词： Conjugate gradient differential evolution evolutionary computation large-scale multi-objective optimization mathematical programming

来源：评论

学校读者我要写书评

暂无评论

A Category Agnostic Model for Visual Rearrangment

A Category Agnostic Model for Visual Rearrangment

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuyi Liu Xinhang Song Weijie Li Xiaohan Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

This paper presents a novel category agnostic model for visual rearrangement task, which can help an embodied agent to physically recover the shuffled scene configuration without any category concepts to the goal configuration. Previous methods usually follow a similar architecture, completing the rearrangement task by aligning the scene changes of the goal and shuffled configuration, according to the semantic scene graphs. However, constructing scene graphs requires the inference of category labels, which not only causes the accuracy drop of the entire task but also limits the application in real world scenario. In this paper, we delve deep into the essence of visual re-arrangement task and focus on the two most essential issues, scene change detection and scene change matching. We utilize the movement and the protrusion of point cloud to accurately identify the scene changes and match these changes depending on the similarity of category agnostic appearance feature. Moreover, to assist the agent to explore the environment more efficiently and comprehensively, we propose a closer-aligned-retrace exploration policy, aiming to observe more details of the scene at a closer distance. We conduct extensive experiments onAI2THOR Rearrangement Challenge based on RoomR dataset and a new multi-room multi-instance dataset MrMiR collected by us. The experimental results demonstrate the effectiveness of our proposed method.

关键词： Point cloud compression Visualization Computer vision Accuracy Semantics Feature extraction Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Classification Between Rumors and Explanations of Rumors Based on Common and Difference Subsequences of Sentences 12th

Classification Between Rumors and Explanations of Rumors Bas...

引用

12th IFIP TC 12 International Conference on intelligent information processing, IIP 2022

作者： Sun, Xiaoping Zhang, Junsheng Sang, Yufei Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Scientific and Technical Information of China Beijing China School of Economics Capital University of Economics and Business Beijing China

ISBN: (纸本)9783031039478

Preventing explosion of rumors on the Internet asks for a quick automatic detection mechanism that can detect rumors according to the given true information. Previous automatic rumors detection models are mainly built by training a supervised classification model on a labeled dataset containing rumor samples and true information samples. However, in many real cases, there is only one short piece of available true information sample given by an authority in form of an explanation or a correction of a rumor. The explanation sample is often short and very similar to rumor samples, making it difficult to train a discriminative classifier to check whether a piece of information is a rumor or an explanation of rumors. It is necessary to build a model to detect whether a short text is a rumor text or an explanation of rumors, which can be used to as evidences for detecting and refuting rumors. In this paper, we presented a sentence preprocessing method that extracts the leftmost longest common sequence to obtain the common and difference subsequences between the rumor text and its explanation text to compose samples and train a supervised model for classification between rumors and explanation of rumors. Experiments show the effectiveness of the proposed method. © 2022, IFIP International Federation for information processing.

关键词： Classification (of information)

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：