Query：
学者姓名：廖祥文
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
多模态生成式摘要往往采用序列到序列(Seq2Seq)框架,目标函数在字符级别优化模型,根据局部最优解生成单词,忽略了摘要样本全局语义信息,使得摘要与多模态信息产生语义偏差,容易造成事实性错误.针对上述问题,提出一种基于语义相关性分析的多模态摘要模型.首先,在Seq2Seq框架基础上对多模态摘要进行训练,生成语义多样性的候选摘要;其次,构建基于语义相关性分析的摘要评估器,从全局的角度学习候选摘要之间的语义差异性和真实评价指标ROUGE(Recall-Oriented Understudy for Gisting Evaluation)的排序模式,从而在摘要样本层面优化模型;最后,不依赖参考摘要,利用摘要评估器对候选摘要进行评价,使得选出的摘要与源文本在语义空间中尽可能相似.实验结果表明,在公开数据集MMSS上,相较于MPMSE(Multimodal Pointer-generator via Multimodal Selective Encoding)模型,所提模型在ROUGE-1、ROUGE-2、ROUGE-L评价指标上分别提升了3.17、1.21和2.24个百分点.
Keyword ：
事实性错误 事实性错误 多模态 多模态 序列到序列 序列到序列 生成式摘要 生成式摘要 语义相关性 语义相关性
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 林于翔 , 吴运兵 , 阴爱英 et al. 基于语义相关性分析的多模态摘要模型 [J]. | 计算机应用 , 2024 , 44 (1) : 65-72 . |
| MLA | 林于翔 et al. "基于语义相关性分析的多模态摘要模型" . | 计算机应用 44 . 1 (2024) : 65-72 . |
| APA | 林于翔 , 吴运兵 , 阴爱英 , 廖祥文 . 基于语义相关性分析的多模态摘要模型 . | 计算机应用 , 2024 , 44 (1) , 65-72 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Mass spectrometry imaging (MSI) is a high-throughput imaging technique capable of the qualitative and quantitative in situ detection of thousands of ions in biological samples. Ion image representation is a technique that produces a low-dimensional vector embedded with significant spectral and spatial information on an ion image, which further facilitates the distance-based similarity measurement for the identification of colocalized ions. However, given the low signal-to-noise ratios inherent in MSI data coupled with the scarcity of annotated data sets, achieving an effective ion image representation for each ion image remains a challenge. In this study, we propose DeepION, a novel deep learning-based method designed specifically for ion image representation, which is applied to the identification of colocalized ions and isotope ions. In DeepION, contrastive learning is introduced to ensure that the model can generate the ion image representation in a self-supervised manner without manual annotation. Since data augmentation is a crucial step in contrastive learning, a unique data augmentation strategy is designed by considering the characteristics of MSI data, such as the Poisson distribution of ion abundance and a random pattern of missing values, to generate plentiful ion image pairs for DeepION model training. Experimental results of rat brain tissue MSI show that DeepION outperforms other methods for both colocalized ion and isotope ion identification, demonstrating the effectiveness of ion image representation. The proposed model could serve as a crucial tool in the biomarker discovery and drug development of the MSI technique.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Guo, Lei , Xie, Chengyi , Miao, Rui et al. DeepION: A Deep Learning-Based Low-Dimensional Representation Model of Ion Images for Mass Spectrometry Imaging [J]. | ANALYTICAL CHEMISTRY , 2024 , 96 (9) : 3829-3836 . |
| MLA | Guo, Lei et al. "DeepION: A Deep Learning-Based Low-Dimensional Representation Model of Ion Images for Mass Spectrometry Imaging" . | ANALYTICAL CHEMISTRY 96 . 9 (2024) : 3829-3836 . |
| APA | Guo, Lei , Xie, Chengyi , Miao, Rui , Xu, Jingjing , Xu, Xiangnan , Fang, Jiacheng et al. DeepION: A Deep Learning-Based Low-Dimensional Representation Model of Ion Images for Mass Spectrometry Imaging . | ANALYTICAL CHEMISTRY , 2024 , 96 (9) , 3829-3836 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
随着生成式人工智能技术的发展，许多领域都得到了帮助与发展，但与此同时虚假信息的构建与传播变得更加简单，虚假信息的检测也随之难度增加.先前的工作主要聚焦于语法问题、内容煽动性等方面的特点，利用深度学习模型对虚假新闻内容进行建模.这样的方式不仅缺乏对内容本身的判断，还无法回溯模型的判别原因.针对上述问题提出一种基于大语言模型隐含语义增强的细粒度虚假新闻检测方法.该方法充分挖掘并利用了现有的生成式大语言模型所具有的总结与推理能力，按照主干事件、细粒度次要事件和隐含信息推理的顺序进行层级式推导，逐步判别新闻的真实性.通过分解任务的方式，该方法最大程度发挥了模型的能力，提高了对虚假新闻的捕获能力，同时该方法也具有一定的可解释性，能够为检测提供判别依据.
Keyword ：
事件抽取 事件抽取 大语言模型 大语言模型 知识增强 知识增强 社交媒体 社交媒体 虚假新闻检测 虚假新闻检测
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 柯婧 , 谢哲勇 , 徐童 et al. 基于大语言模型隐含语义增强的细粒度虚假新闻检测方法 [J]. | 计算机研究与发展 , 2024 , 61 (05) : 1250-1260 . |
| MLA | 柯婧 et al. "基于大语言模型隐含语义增强的细粒度虚假新闻检测方法" . | 计算机研究与发展 61 . 05 (2024) : 1250-1260 . |
| APA | 柯婧 , 谢哲勇 , 徐童 , 陈宇豪 , 廖祥文 , 陈恩红 . 基于大语言模型隐含语义增强的细粒度虚假新闻检测方法 . | 计算机研究与发展 , 2024 , 61 (05) , 1250-1260 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Mass spectrometry imaging (MSI) is a high-throughput imaging technique capable of the qualitative and quantitative in situ detection of thousands of ions in biological samples. Ion image representation is a technique that produces a low-dimensional vector embedded with significant spectral and spatial information on an ion image, which further facilitates the distance-based similarity measurement for the identification of colocalized ions. However, given the low signal-to-noise ratios inherent in MSI data coupled with the scarcity of annotated data sets, achieving an effective ion image representation for each ion image remains a challenge. In this study, we propose DeepION, a novel deep learning-based method designed specifically for ion image representation, which is applied to the identification of colocalized ions and isotope ions. In DeepION, contrastive learning is introduced to ensure that the model can generate the ion image representation in a self-supervised manner without manual annotation. Since data augmentation is a crucial step in contrastive learning, a unique data augmentation strategy is designed by considering the characteristics of MSI data, such as the Poisson distribution of ion abundance and a random pattern of missing values, to generate plentiful ion image pairs for DeepION model training. Experimental results of rat brain tissue MSI show that DeepION outperforms other methods for both colocalized ion and isotope ion identification, demonstrating the effectiveness of ion image representation. The proposed model could serve as a crucial tool in the biomarker discovery and drug development of the MSI technique.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Guo, Lei , Xie, Chengyi , Miao, Rui et al. DeepION: A Deep Learning-Based Low-Dimensional Representation Model of Ion Images for Mass Spectrometry Imaging [J]. | ANALYTICAL CHEMISTRY , 2024 , 96 (9) : 3829-3836 . |
| MLA | Guo, Lei et al. "DeepION: A Deep Learning-Based Low-Dimensional Representation Model of Ion Images for Mass Spectrometry Imaging" . | ANALYTICAL CHEMISTRY 96 . 9 (2024) : 3829-3836 . |
| APA | Guo, Lei , Xie, Chengyi , Miao, Rui , Xu, Jingjing , Xu, Xiangnan , Fang, Jiacheng et al. DeepION: A Deep Learning-Based Low-Dimensional Representation Model of Ion Images for Mass Spectrometry Imaging . | ANALYTICAL CHEMISTRY , 2024 , 96 (9) , 3829-3836 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The advancement of generative artificial intelligence technology has significantly contributed to the progress in various fields. However, this technological development has also inadvertently facilitated the creation and widespread dissemination of misinformation. Prior research has concentrated on addressing grammatical issues, inflammatory content, and other pertinent features by employing deep learning models to characterize and model deceptive elements within fake news content. These approaches not only are lack of the capability to assess the content itself, but also fall short in elucidating the reasons behind the model's classification. Based on the above problems, we propose a fine-grained fake news detection method with implicit semantic enhancement. This method fully utilizes the summarization and reasoning capabilities of the existing generative large language model. The method employs inference based on major events, fine-grained minor events, and implicit information to systematically evaluate the authenticity of news content. This method strategically leverages the full potential of the model by decomposing tasks, thereby not only optimizing its proficiency but also significantly enhancing its prowess in capturing instances of fake news. Simultaneously, it is designed to be interpretable, providing a solid foundation for detection. With its inherent ability, this method not only ensures reliable identification but also holds vast potential for diverse applications. © 2024 Science Press. All rights reserved.
Keyword ：
Computational linguistics Computational linguistics Deep learning Deep learning Fake detection Fake detection Semantics Semantics Social networking (online) Social networking (online)
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Jing, Ke , Zheyong, Xie , Tong, Xu et al. An Implicit Semantic Enhanced Fine-Grained Fake News Detection Method Based on Large Language Models [J]. | Computer Research and Development , 2024 , 61 (5) : 1250-1260 . |
| MLA | Jing, Ke et al. "An Implicit Semantic Enhanced Fine-Grained Fake News Detection Method Based on Large Language Models" . | Computer Research and Development 61 . 5 (2024) : 1250-1260 . |
| APA | Jing, Ke , Zheyong, Xie , Tong, Xu , Yuhao, Chen , Xiangwen, Liao , Enhong, Chen . An Implicit Semantic Enhanced Fine-Grained Fake News Detection Method Based on Large Language Models . | Computer Research and Development , 2024 , 61 (5) , 1250-1260 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Empathetic response generation endeavors to empower dialogue systems to perceive speakers' emotions and generate empathetic responses accordingly. Psychological research demonstrates that emotion, as an essential factor in empathy, encompasses trait emotions, which are static and context-independent, and state emotions, which are dynamic and context-dependent. However, previous studies treat them in isolation, leading to insufficient emotional perception of the context, and subsequently, less effective empathetic expression. To address this problem, we propose Combining Trait and State emotions for Empathetic Response Model (CTSM). Specifically, to sufficiently perceive emotions in dialogue, we first construct and encode trait and state emotion embeddings, and then we further enhance emotional perception capability through an emotion guidance module that guides emotion representation. In addition, we propose a cross-contrastive learning decoder to enhance the model's empathetic expression capability by aligning trait and state emotions between generated responses and contexts. Both automatic and manual evaluation results demonstrate that CTSM outperforms state-of-the-art baselines and can generate more empathetic responses. Our code is available at https://github.com/wangyufeng-empty/CTSM. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.
Keyword ：
Behavioral research Behavioral research Emotion Recognition Emotion Recognition Learning systems Learning systems Speech processing Speech processing Speech recognition Speech recognition
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Yufeng , Chen, Chao , Yang, Zhou et al. CTSM: Combining Trait and State Emotions for Empathetic Response Model [C] . 2024 : 4214-4225 . |
| MLA | Wang, Yufeng et al. "CTSM: Combining Trait and State Emotions for Empathetic Response Model" . (2024) : 4214-4225 . |
| APA | Wang, Yufeng , Chen, Chao , Yang, Zhou , Wang, Shuhui , Liao, Xiangwen . CTSM: Combining Trait and State Emotions for Empathetic Response Model . (2024) : 4214-4225 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Empathetic response generation endeavours to perceive the interlocutor's emotional and cognitive states in the dialogue and express proper responses. Previous studies detect the interlocutor's states by understanding the immediate context of the dialogue. However, these methods are at an elementary/intermediate level of empathetic understanding due to the neglect of the broader context (i.e., the situation) and its associations with the dialogue, leading to inaccurate comprehension of the interlocutor's states. In this paper, we utilize the EMPATHETIC-DIALOGUES dataset consisting of 25k dialogues, and on this basis, we propose a Situation-Dialogue Association Model (SDAM). SDAM focuses on the broader context, i.e., the situation, and enhances the understanding of empathy from explicit and implicit associations. Regarding explicit associations, we propose a bidirectional filtering encoder. It selects relevant keywords between the situation and dialogue, learning their direct lexical relevance. For implicit associations, we use a knowledge-based hypergraph network grounded to learn convoluted connections between the situation and the dialogue. Moreover, we also introduce a simple finetuning approach that combines SDAM with large language models to further strengthen the empathetic understanding capability. Compared to the baseline, SDAM demonstrates superior empathetic ability. In terms of emotion accuracy, fluency, and response diversity (Distinct1/Distinct-2), SDAM achieves improvements of 12.25 (a 30.47% increase), 0.3 (a 0.85% increase), and 0.86/1.23 (116.22% and 30.67% increases), respectively. Additionally, our variant model based on large language models exhibits better emotion recognition capability without compromising response quality, specifically achieving an improvement of 0.23 (a 0.37% increase) in emotion accuracy.
Keyword ：
Emotional detection Emotional detection Empathetic response generation Empathetic response generation Natural language processing Natural language processing Text generation Text generation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yang, Zhou , Ren, Zhaochun , Wang, Yufeng et al. Situation-aware empathetic response generation [J]. | INFORMATION PROCESSING & MANAGEMENT , 2024 , 61 (6) . |
| MLA | Yang, Zhou et al. "Situation-aware empathetic response generation" . | INFORMATION PROCESSING & MANAGEMENT 61 . 6 (2024) . |
| APA | Yang, Zhou , Ren, Zhaochun , Wang, Yufeng , Sun, Haizhou , Zhu, Xiaofei , Liao, Xiangwen . Situation-aware empathetic response generation . | INFORMATION PROCESSING & MANAGEMENT , 2024 , 61 (6) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
提出一种从整体到局部优化的风格迁移(global-local based style transfer, G-LST)模型.首先，利用广泛的源端数据进行迭代优化来自动构建高质量的伪平行数据，并通过联合训练来提升模型对整体风格的语义感知；随后，利用常识性知识修正词级的细粒度风格来增强局部风格的表现，同时兼顾整体与局部风格，提高风格转换的准确度.基于GYAFC数据集的实验结果表明，相较于目前表现最佳的文本风格迁移模型，G-LST模型在E&M与F&R两个领域数据上的风格转换准确率分别提高了2.70%和4.47%,内容保留与风格准确率的综合指标分别提升了1.18%和1.95%.
Keyword ：
常识性知识 常识性知识 文本风格迁移 文本风格迁移 联合训练 联合训练 迭代优化 迭代优化
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 范剑宏 , 杨州 , 蔡铁城 et al. 从整体到局部优化的文本风格迁移模型 [J]. | 福州大学学报(自然科学版) , 2024 , 52 (04) : 413-420 . |
| MLA | 范剑宏 et al. "从整体到局部优化的文本风格迁移模型" . | 福州大学学报(自然科学版) 52 . 04 (2024) : 413-420 . |
| APA | 范剑宏 , 杨州 , 蔡铁城 , 吴运兵 , 廖祥文 . 从整体到局部优化的文本风格迁移模型 . | 福州大学学报(自然科学版) , 2024 , 52 (04) , 413-420 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Empathetic response generation endeavors to empower dialogue systems to perceive speakers' emotions and generate empathetic responses accordingly. Psychological research demonstrates that emotion, as an essential factor in empathy, encompasses trait emotions, which are static and context-independent, and state emotions, which are dynamic and context-dependent. However, previous studies treat them in isolation, leading to insufficient emotional perception of the context, and subsequently, less effective empathetic expression. To address this problem, we propose Combining Trait and State emotions for Empathetic Response Model (CTSM). Specifically, to sufficiently perceive emotions in dialogue, we first construct and encode trait and state emotion embeddings, and then we further enhance emotional perception capability through an emotion guidance module that guides emotion representation. In addition, we propose a cross-contrastive learning decoder to enhance the model's empathetic expression capability by aligning trait and state emotions between generated responses and contexts. Both automatic and manual evaluation results demonstrate that CTSM outperforms state-of-the-art baselines and can generate more empathetic responses. Our code is available at https://github.com/wangyufeng-empty/CTSM. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.
Keyword ：
contrastive learning contrastive learning dialogue system dialogue system emotion recognition emotion recognition empathetic response generation empathetic response generation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Y. , Chen, C. , Yang, Z. et al. CTSM: Combining Trait and State Emotions for Empathetic Response Model [未知]. |
| MLA | Wang, Y. et al. "CTSM: Combining Trait and State Emotions for Empathetic Response Model" [未知]. |
| APA | Wang, Y. , Chen, C. , Yang, Z. , Wang, S. , Liao, X. . CTSM: Combining Trait and State Emotions for Empathetic Response Model [未知]. |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
提出一种多层次自适应知识蒸馏方法,以提升轻量化模型的性能.首先,针对遥感影像类别间差异程度不均衡的问题,通过改进输出层知识蒸馏中的温度机制,提出一种自适应温度机制,促进学生模型更好地学习大且深的教师模型输出层概率分布知识;然后,通过添加辅助卷积块来融入特征层的知识蒸馏方法,使学生模型学习教师模型的多层次知识;最后,在UCM、AID和NWPU这 3 个公开数据集上进行实验.结果表明:所提方法蒸馏后的学生模型参数量仅为教师模型的 6%,其分类精度较蒸馏前最多可提升 7.78%,比其他网络模型更便于部署在末端.
Keyword ：
卷积神经网络 卷积神经网络 场景分类 场景分类 特征蒸馏 特征蒸馏 知识蒸馏 知识蒸馏 自适应温度蒸馏 自适应温度蒸馏
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 翁谦 , 黄志铭 , 林嘉雯 et al. 多层次自适应知识蒸馏的轻量化高分遥感场景分类 [J]. | 福州大学学报（自然科学版） , 2023 , 51 (4) : 459-466 . |
| MLA | 翁谦 et al. "多层次自适应知识蒸馏的轻量化高分遥感场景分类" . | 福州大学学报（自然科学版） 51 . 4 (2023) : 459-466 . |
| APA | 翁谦 , 黄志铭 , 林嘉雯 , 简彩仁 , 廖祥文 . 多层次自适应知识蒸馏的轻量化高分遥感场景分类 . | 福州大学学报（自然科学版） , 2023 , 51 (4) , 459-466 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
