检索结果-内蒙古大学图书馆

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

作者： Zhu, Dawei Wang, Liang Yang, Nan Song, Yifan Wu, Wenhao Wei, Furu Li, Sujian School of Computer Science Peking University China National Key Laboratory for Multimedia Information Processing Peking University China Jiangsu Collaborative Innovation Center for Language Ability Jiangsu Normal University China Microsoft Corporation United States

ISBN: (纸本)9798891761643

Embedding models play a pivotal role in modern NLP applications such as document retrieval. However, existing embedding models are limited to encoding short documents of typically 512 tokens, restrained from application scenarios requiring long inputs. This paper explores context window extension of existing embedding models, pushing their input length to a maximum of 32,768. We begin by evaluating the performance of existing embedding models using our newly constructed LONGEMBED benchmark, which includes two synthetic and four real-world tasks, featuring documents of varying lengths and dispersed target information. The benchmarking results highlight huge opportunities for enhancement in current models. Via comprehensive experiments, we demonstrate that training-free context window extension strategies can effectively increase the input length of these models by several folds. Moreover, comparison of models using Absolute Position Encoding (APE) and Rotary Position Encoding (RoPE) reveals the superiority of RoPE-based embedding models in context window extension, offering empirical guidance for future models. Our benchmark, code and trained models will be released to advance the research in long context embedding models. © 2024 Association for Computational Linguistics.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Overview of CCL24-Eval Task 8: Evaluation of Commonsense Reasoning and Moral Understanding in Children’s Stories 23

引用

23rd Chinese National Conference on Computational Linguistics, CCL 2024

作者： Yan, Guohang Liang, Feihao Guo, Yaxin Tan, Hongye Li, Ru Zhang, Hu School of Computer and Information Technology Shanxi University Shanxi Taiyuan030006 China Key Laboratory of Computational Intelligence and Chinese Information Processing Ministry of Education Shanxi University Shanxi Taiyuan030006 China

ISBN: (纸本)9780000000002

This paper provides a comprehensive review of the the CCL24-Eval Task 8: Commonsense Reasoning and Moral Understanding in Children’s Stories(CRMUS). This task has designed two sub-tasks, which aim to assess the commonsense reasoning and implicit meaning comprehension capabilities of Large Language Models(LLMs). We heve received registration forms from 33 teams, 15 of which submitted final results that exceeded the baseline score. We present the results of the top 5 teams and our analysis of these results. © 2024 China National Conference on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Evidential Open Set Recognition for Imbalanced Medical Images via Multi-level Data Augmentation

Evidential Open Set Recognition for Imbalanced Medical Image...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhao, Rui-Wei Xu, Yiqian Zhang, Ying Feng, Rui Shanghai Maritime University College of Information Engineering China Fudan University Academy for Engineering and Technology China Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)9798350386226

Due to the exstence of common and rare diseases, the complex clinical scenario often poses the challenging class imbalanced open set recognition problem. Unfortunately, most existing approaches are ill-suited for such situations with limited and imbalanced data during training and the possibility of encountering unseen classes during test. In this work, we propose a novel Multi-level mixup-based Evidential Open Set Recognition (ME-OSR) approach to more explicitly and effectively address the open set recognition for class-imbalanced medical images. Briefly, we first extract disentangled discriminative and background image features. Then, based on the original images and extracted features, we propose to sample and conduct Multi-level Open Mixup (MOM) for a more balanced open set data augmentation. It includes extensive intra- and interclass mixup operations in both image and feature spaces, which can augment rare classes with different feature combinations and generate potential pseudo-unknown class examples in the open set to boost the model training. Based on the augmented data and their extracted discriminative features, we propose a Regularized Evidential Deep Learning (REDL) classifier to work with the augmented data to achieve open set recognition with prediction uncertainty estimation and unknown example rejection. Through comparative experiments and ablation studies on several representative medical datasets, we showed that our proposed method outperforms other state-of-the-arts on four popular medical OSR datasets. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Hybrid particle swarm optimization with adaptive learning strategy

引用

Soft Computing 2024年第17-18期28卷 9759-9784页

作者： Wang, Lanyu Tian, Dongping Gou, Xiaorui Shi, Zhongzhi School of Mathematics and Information Sciences Baoji University of Arts and Science Shaanxi Baoji721007 China Institute of Computer Software Baoji University of Arts and Sciences Shaanxi Baoji721007 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

Particle swarm optimization (PSO) is a meta-heuristic algorithm that can be used to solve different real-world optimization problems. However, PSO suffers from some intrinsic drawbacks, including falling into local optimal and slow convergence in the latter evolution process. To deal with these issues, a hybrid PSO with adaptive learning strategy (abbreviated as HPSO-ALS) is proposed in this paper. To start with, the chaotic opposition-learning method is employed to generate the uniformly distributed particles so as to enhance the quality of the initial swarm. Next, a self-logical mapping-based nonlinear decreasing inertia weight is formulated to trade off the global search and local search abilities. Meanwhile, different adaptive position updating strategies are leveraged to achieve better convergence according to different evolution status. In addition, inspired by the cask effect, the global worst particle (gworst) is introduced into the velocity updating to make full use of the potential information of the particles. Finally, extensive experiments on sixteen benchmark functions and CEC’13 test suite have verified the promising performance of HPSO-ALS proposed in this paper. Alternatively, HPSO-ALS is also applied to the classical traveling salesman problem (TSP) and the experimental results have further validated the effectiveness and efficiency of our proposal. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

Toward Comprehensive Semantic Prompt for Region Contrastive Learning Underwater Image Enhancement

Toward Comprehensive Semantic Prompt for Region Contrastive ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Wang, Xiao Fu, Yongsheng Wang, Wei Liu, Wei School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System China

ISBN: (纸本)9798350368741

Underwater image enhancement (UIE) focuses on mitigating image quality degradation due to light absorption and scattering. However, most existing methods enhance images via a global and uniform manner, neglecting the inherent semantic information in different regions, which may cause the network to easily deviate from the region's original color. Moreover, these methods typically rely on clear images to guide network convergence, a process constrained by the limited availability of real-world datasets, making it extremely challenging to train enhancement models for various degradations. To address these challenges, this paper introduces a semantic guidance and region contrastive constraints network (SRCNet). Initially, we propose a semantic-aware RWKV (Receptance Weighted key Value) block and a semantic prompt regularization module. These components leverage intra-target semantic correlations to preserve image details and colors within a global perceptual framework, while employing focal loss to emphasize the restoration of severely degraded regions. Subsequently, we introduce a region contrastive learning method that effectively utilizes negative samples to precisely capture features sensitive to degradation factors, thereby fostering robust feature distributions. Finally, experimental results demonstrate that our method outperforms existing state-of-the-art (SOTA) approaches. © 2025 IEEE.

关键词： contrastive learning rwkv semantic prompt Underwater image enhancement

来源：评论

学校读者我要写书评

暂无评论

EERPD: Leveraging Emotion and Emotion Regulation for Improving Personality Detection 31

EERPD: Leveraging Emotion and Emotion Regulation for Improvi...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Li, Zheng Zhu, Dawei Ma, Qilong Xiong, Weimin Li, Sujian School of Computer Science Peking University China State Key Laboratory for Multimedia Information Processing Peking University China School of Software BNRist Tsinghua University China Jiangsu Collaborative Innovation Center for Language Ability Jiangsu Normal University China

ISBN: (纸本)9798891761964

Personality is a fundamental construct in psychology, reflecting an individual's behavior, thinking, and emotional patterns. While previous researches have made progress in personality detection, their designed methods generally overlook the important connection between psychological knowledge "emotion regulation" and personality traits. Based on this, we propose a new personality detection method called EERPD. This method introduces the use of emotion regulation, a psychological concept highly correlated with personality, for personality prediction. By combining this concept with emotion features, EERPD retrieves few-shot examples and provides process CoTs for inferring labels from text. This approach enhances the understanding of LLM for personality implicit within text and improves the performance in personality detection. Experimental results demonstrate that EERPD significantly enhances the accuracy and robustness of personality detection, outperforming previous SOTA by 15.05/4.29 in average F1 on the two benchmark datasets. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Shapley Value-based Contrastive Alignment for Multimodal information Extraction 24

Shapley Value-based Contrastive Alignment for Multimodal Inf...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Luo, Wen Xia, Yu Tianshu, Shen Li, Sujian State Key Laboratory of Multimedia Information Processing Peking University Beijing China School of Computer Science Peking University Beijing China Wangxuan Institute of Computer Technology Peking University Beijing China

ISBN: (纸本)9798400706868

The rise of social media and the exponential growth of multimodal communication necessitates advanced techniques for Multimodal information Extraction (MIE). However, existing methodologies primarily rely on direct Image-Text interactions, a paradigm that often faces significant challenges due to semantic and modality gaps between images and text. In this paper, we introduce a new paradigm of Image-Context-Text interaction, where large multimodal models (LMMs) are utilized to generate descriptive textual context to bridge these gaps. In line with this paradigm, we propose a novel Shapley Value-based Contrastive Alignment (Shap-CA) method, which aligns both context-text and context-image pairs. Shap-CA initially applies the Shapley value concept from cooperative game theory to assess the individual contribution of each element in the set of contexts, texts and images towards total semantic and modality overlaps. Following this quantitative evaluation, a contrastive learning strategy is employed to enhance the interactive contribution within context-text/image pairs, while minimizing the influence across these pairs. Furthermore, we design an adaptive fusion module for selective cross-modal fusion. Extensive experiments across four MIE datasets demonstrate that our method significantly outperforms existing state-of-the-art methods. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

MDDMamba: A Model for Multi-Modal Depression Detection with a Memory-Saving Cross-Modal Attention Mechanism Based on Mamba

MDDMamba: A Model for Multi-Modal Depression Detection with ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Mingzhou Wang, Zheyu Liu, Feng Nanjing University of Posts and Telecommunications School of Education Science and Technology Nanjing210023 China Nanjing University of Science and Technology ZiJin College School of Computer and Artificial Intelligence Nanjing210023 China Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology Nanjing210003 China

ISBN: (纸本)9798350386226

Depression is a severe mental health disorder that constitutes a significant global health challenge, necessitating efficient and accurate automated diagnostic tools. Traditional approaches to automated depression assessment using multi-modal data often face three significant difficulties: small sample sizes in available datasets, high computational cost, and difficulties in effectively integrating different modalities. In this paper, we first mitigate the problem of dataset quality by utilizing an estimated imputation strategy for missing values based on a known data augmentation method. Additionally, we introduce a multi-modal depression detection model named MDDMamba, designed to address the latter two challenges by integrating features from pre-trained emotion models with the memory-efficient selective state space model named Mamba. The MDDMamba model combines features from pre-trained emotion models for both text and audio, enhancing the extraction of emotional information. The core of the MDDMamba model is the CrossMamba module, which replaces the traditional Transformer's quadratic computational complexity with a linear complexity alternative, facilitating efficient multi-modal fusion. Experimental results on CMDC and EATD-Corpus datasets show that the MDDMamba model achieves better classification and regression performance and stronger generalization capabilities in depression detection. Notably, the MDDMamba model achieves an F1 score of 0.94 and a Pearson correlation coefficient of 0.86 on the CMDC dataset while maintaining lower memory cost, outperforming most advanced multi-modal depression detection methods across various experimental scenarios. © 2024 IEEE.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Enhanced BERT with Graph and Topic information for Short Text Classification 35

Enhanced BERT with Graph and Topic Information for Short Tex...

引用

35th International Conference on Software Engineering and Knowledge Engineering, SEKE 2023

作者： Zhang, Tong Tang, Ailing Yan, Rong College of Computer Science Inner Mongolia University Inner Mongolia Key Laboratory of Mongolian Information Processing Technology National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot010021 China

Short text classification is an important natural language processing task due to the prevalence of short text on the internet and social media platforms. In this paper, we propose a novel graph-based short text classification method named GBBM (Graph-BERT-BTM Model) that leverages the powerful representation ability of graph data to capture the structural features of short text. In this work, we incorporate topic information to enrich and expand the feature space for the short text and compare our proposed method on five publicly available short text datasets with five existing models. Experimental results indicate the superiority of our proposed method. © 2023 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Attention information Fusion Emotion Analysis Model Based on BiLSTM-BERT 4

Attention Information Fusion Emotion Analysis Model Based on...

引用

4th International Conference on Consumer Electronics and computer Engineering, ICCECE 2024

作者： Cheng, Zhi-Wei Li, Shun-Xin Wuhan University of Science and Technology Department of Computer Science and Technology Wuhan China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial Wuhan China

ISBN: (纸本)9798350384062

Aiming at the problem that most sentiment analysis methods do not focus on the weight fusion of local context and global context information and the important information in fusion features is not prominent, AIFM-BB (Attention information fusion emotion analysis model based on BiLSTM-BERT) is proposed. The model uses a pre-trained BERT model to process text vectors and a collaborative speech analysis algorithm to process audio vectors, and introduces BiLSTM and Attention mechanisms. The weight of the feature vector is dynamically adjusted by combining the global information and local information of text and audio and the attention information of text and audio modes. The emotion analysis results are obtained through the Softmax layer after the fusion features are self-focused. The experimental results show that the accuracy of the proposed AIFM-BB model on the CMU-MOSI dataset is 85.3%, which is 2.8 percentage points higher than the baseline. In the multi-category emotion classification task, the accuracy of the model is 44.7%, an improvement of 1.1 percentage points compared with baseline. The accuracy is 83.6% on the CMU-MOSEI dataset, an improvement of 1.4 percentage points compared to baseline. © 2024 IEEE.

关键词： Sentiment analysis

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：