Query:
学者姓名:杜永萍
Refining:
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract :
Multimodal aspect-based sentiment analysis (MABSA) aims to predict the sentiment of aspect by the fusion of different modalities such as image, text and so on. However, the availability of high-quality multimodal data remains limited. Therefore, few-shot MABSA is a new challenge. Previous works are rarely able to cope with low-resource and few-shot scenarios. In order to address the above problems, we design a Few-shot Multimodal aspect-based sentiment analysis framework based on Contrastive Finetuning (FMCF). Initially, the image modality is transformed to the corresponding textual caption to achieve the entailed semantic information and a contrastive dataset is constructed based on similarity retrieval for finetuning in the following stage. Further, a sentence encoder is trained based on SBERT, which combines supervised contrastive learning and sentence-level multi-feature fusion to complete MABSA. The experiments demonstrate that our framework achieves excellent performance in the few-shot scenarios. Importantly, with only 256 training samples and limited computational resources, the proposed method outperforms fine-tuned models that use all available data on the Twitter dataset.
Keyword :
Aspect-based sentiment analysis Aspect-based sentiment analysis Few-shot learning Few-shot learning Contrastive learning Contrastive learning Multimodal fusion Multimodal fusion
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Du, Yongping , Xie, Runfeng , Zhang, Bochao et al. FMCF: Few-shot Multimodal aspect-based sentiment analysis framework based on Contrastive Finetuning [J]. | APPLIED INTELLIGENCE , 2024 . |
MLA | Du, Yongping et al. "FMCF: Few-shot Multimodal aspect-based sentiment analysis framework based on Contrastive Finetuning" . | APPLIED INTELLIGENCE (2024) . |
APA | Du, Yongping , Xie, Runfeng , Zhang, Bochao , Yin, Zihao . FMCF: Few-shot Multimodal aspect-based sentiment analysis framework based on Contrastive Finetuning . | APPLIED INTELLIGENCE , 2024 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Multi-hop reasoning is critical for natural language understanding but poses challenges for current models, requiring models capable of aggregating and reasoning across multiple sources of information. We propose an Adversarial Entity Graph Convolutional Network (AEGCN) to improve multi-hop inference performance. Unlike previous GNNs-based models, AEGCN places a greater emphasis on the construction of rich entity graph which focuses on identifying the related entities from support document and connecting these entities with innovative edge relationships. The entity graph built by AEGCN preserves both the semantic information and structure of the original text. Further, adversarial training is adopted to generate challenging embeddings for the entity graph, increasing the model's robustness against the interference. The experiments evaluated on WIKIHOP and MEDHOP dataset indicate that AEGCN achieves 6.8 % and 7.7 % accuracy improvement over baseline model respectively, confirming the model's advanced capability in multi-hop reasoning tasks.
Keyword :
Multi-hop reasoning Multi-hop reasoning Graph neural networks Graph neural networks Question answering Question answering Adversarial training Adversarial training
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Du, Yongping , Yan, Rui , Hou, Ying et al. Adversarial Entity Graph Convolutional Networks for multi-hop inference question answering [J]. | EXPERT SYSTEMS WITH APPLICATIONS , 2024 , 258 . |
MLA | Du, Yongping et al. "Adversarial Entity Graph Convolutional Networks for multi-hop inference question answering" . | EXPERT SYSTEMS WITH APPLICATIONS 258 (2024) . |
APA | Du, Yongping , Yan, Rui , Hou, Ying , Pei, Yu , Han, Honggui . Adversarial Entity Graph Convolutional Networks for multi-hop inference question answering . | EXPERT SYSTEMS WITH APPLICATIONS , 2024 , 258 . |
Export to | NoteExpress RIS BibTex |
Abstract :
A large number of unanswered products-related questions appear in the E-commerce platforms, necessitating the deployment of question-answering models to automatically provide precise responses for the user. However, the substantial absence of ground truth presents challenges for implementing supervised learning, and existing unsupervised contrastive learning methods have not addressed this issue fundamentally, with limitations in integrating multi-level features. This paper presents a dual-tower cross-biased contrastive learning model for answer selection, named CCLM-AS. By taking questions and augmented product reviews as positive pairs for unsupervised contrastive learning and employing a dual-tower structure encoder, CCLM-AS learns sentence representations from unlabeled data effectively. Furthermore, the designed training objective realizes multi-level feature integration, including character, sentence and dialogue levels, which enhances the model's inference ability. The experimental results on AmazonQA dataset indicate that our proposed model outperforms existing contrastive learning-based sentence representation models and also achieves comparable performance to supervised answer selection models. This demonstrates that CCLM-AS can not only alleviate the data sparsity problem effectively but also retain the excellent performance.
Keyword :
Multi-level feature fusion Multi-level feature fusion Data augmentation Data augmentation Answer selection Answer selection Product-related question answering Product-related question answering Contrastive learning Contrastive learning
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Jin, Xingnan , Du, Yongping , Wang, Binrui et al. Cross-biased contrastive learning for answer selection with dual-tower structure [J]. | NEUROCOMPUTING , 2024 , 610 . |
MLA | Jin, Xingnan et al. "Cross-biased contrastive learning for answer selection with dual-tower structure" . | NEUROCOMPUTING 610 (2024) . |
APA | Jin, Xingnan , Du, Yongping , Wang, Binrui , Zhang, Qi . Cross-biased contrastive learning for answer selection with dual-tower structure . | NEUROCOMPUTING , 2024 , 610 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Ant colony optimization (ACO) algorithm is widely used in the instant delivery order scheduling because of its distributed computing capability. However, the order delivery efficiency decreases when different logistics statuses are faced. In order to improve the performance of ACO, an adaptive ACO algorithm based on real-time logistics features (AACO-RTLFs) is proposed. First, features are extracted from the event dimension, spatial dimension, and time dimension of the instant delivery to describe the real-time logistics status. Five key factors are further selected from the above three features to assist in problem modeling and ACO designing. Second, an adaptive instant delivery model is built considering the customer's acceptable delivery time. The acceptable time is calculated by emergency order mark and weather conditions in the event dimension feature. Third, an adaptive ACO algorithm is proposed to obtain the instant delivery order schedules. The parameters of the probability equation in ACO are adjusted according to the extracted key factors. Finally, the Gurobi solver in Python is used to perform numerical experiments on the classical datasets to verify the effectiveness of the instant delivery model. The proposed AACO-RTLF algorithm shows its advantages in instant delivery order scheduling when compared to the other state-of-the-art algorithms.
Keyword :
Vehicle dynamics Vehicle dynamics Feature extraction Feature extraction instant delivery instant delivery Information entropy Information entropy Heuristic algorithms Heuristic algorithms logistics status logistics status real-time logistics feature real-time logistics feature Adaptation models Adaptation models Real-time systems Real-time systems Logistics Logistics feature extraction feature extraction Ant colony optimization (ACO) algorithm Ant colony optimization (ACO) algorithm
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Hou, Ying , Guo, Xinyu , Han, Honggui et al. Adaptive Ant Colony Optimization Algorithm Based on Real-Time Logistics Features for Instant Delivery [J]. | IEEE TRANSACTIONS ON CYBERNETICS , 2024 . |
MLA | Hou, Ying et al. "Adaptive Ant Colony Optimization Algorithm Based on Real-Time Logistics Features for Instant Delivery" . | IEEE TRANSACTIONS ON CYBERNETICS (2024) . |
APA | Hou, Ying , Guo, Xinyu , Han, Honggui , Wang, Jingjing , Du, Yongping . Adaptive Ant Colony Optimization Algorithm Based on Real-Time Logistics Features for Instant Delivery . | IEEE TRANSACTIONS ON CYBERNETICS , 2024 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Sequential recommendation becomes a critical task in many application scenarios, since people's online activities are increasing. In order to predict the next item that users may be interested, it is necessary to take both general and dynamic preferences of the user into account. Existing approaches typically integrate the useritem or item-item feature interactions directly without considering the dynamic changes of the user's long-term and short-term preferences, which also limits the capability of the model. To address these issues, we propose a novel unified framework for sequential recommendation task, modeling users' long and short-term sequential behaviors at each time step and capturing item-to-item dependencies in higher-order by hierarchical attention mechanism. The proposed model considers the dynamic long and short-term user preferences simultaneously, and a joint learning mechanism is introduced to fuse them for better recommendation. We extensively evaluate our model with several state-of-the-art methods by different validation metrics on three real-world datasets. The experimental results demonstrate the significant improvement of our approach over other compared models.
Keyword :
Behavior sequences Behavior sequences Hierarchical attention Hierarchical attention Feature interactions Feature interactions Long and short-term preferences Long and short-term preferences Sequential recommendation Sequential recommendation
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Du, Yongping , Peng, Zhi , Niu, Jinyu et al. A unified hierarchical attention framework for sequential recommendation by fusing long and short-term preferences [J]. | EXPERT SYSTEMS WITH APPLICATIONS , 2022 , 201 . |
MLA | Du, Yongping et al. "A unified hierarchical attention framework for sequential recommendation by fusing long and short-term preferences" . | EXPERT SYSTEMS WITH APPLICATIONS 201 (2022) . |
APA | Du, Yongping , Peng, Zhi , Niu, Jinyu , Yan, Jingya . A unified hierarchical attention framework for sequential recommendation by fusing long and short-term preferences . | EXPERT SYSTEMS WITH APPLICATIONS , 2022 , 201 . |
Export to | NoteExpress RIS BibTex |
Abstract :
summarization models can generate summary auto-regressively, but the quality is often impacted by the noise in the text. Learning cross-sentence relations is a crucial step in this task and the graph-based network is more effective to capture the sentence relationship. Moreover, knowledge is very important to distinguish the noise of the text in special domain. A novel model structure called UGDAS is proposed in this paper, which combines a sentence-level denoiser based on an unsupervised graph-network and an auto-regressive generator. It utilizes domain knowledge and sentence position information to denoise the original text and further improve the quality of generated summaries. We use the recently-introduced dataset CORD-19 (COVID-19 Open Research Dataset) on text summarization task, which contains large-scale data on coronaviruses. The experimental results show that our model achieves the SOTA (state-of-the-art) result on CORD-19 dataset and outperforms the related baseline models on the PubMed Abstract dataset.
Keyword :
Graph-network Graph-network Domain knowledge Domain knowledge Abstractive summarization Abstractive summarization Pre-trained language model Pre-trained language model
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Du, Yongping , Zhao, Yiliang , Yan, Jingya et al. UGDAS: Unsupervised graph-network based denoiser for abstractive summarization in biomedical domain [J]. | METHODS , 2022 , 203 : 160-166 . |
MLA | Du, Yongping et al. "UGDAS: Unsupervised graph-network based denoiser for abstractive summarization in biomedical domain" . | METHODS 203 (2022) : 160-166 . |
APA | Du, Yongping , Zhao, Yiliang , Yan, Jingya , Li, Qingxiao . UGDAS: Unsupervised graph-network based denoiser for abstractive summarization in biomedical domain . | METHODS , 2022 , 203 , 160-166 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Sentiment classification can explore the opinions expressed by people and help them make better decisions. With the increasing of multimodal contents on the web, such as text, image, audio and video, how to make full use of them is important in many tasks, including sentiment classification. This paper focuses on the text and image. Previous work cannot capture the fine-grained features of images, and those models bring a lot of noise during feature fusion. In this work, we propose a novel multimodal sentiment classification model based on gated attention mechanism. The image feature is used to emphasize the text segment by the attention mechanism and it allows the model to focus on the text that affects the sentiment polarity. Moreover, the gating mechanism enables the model to retain useful image information while ignoring the noise introduced during the fusion of image and text. The experiment results on Yelp multimodal dataset show that our model outperforms the previous SOTA model. And the ablation experiment results further prove the effectiveness of different strategies in the proposed model. (C) 2022 Elsevier B.V. All rights reserved.
Keyword :
Convolutional neural network Convolutional neural network Multimodal sentiment classification Multimodal sentiment classification Gated attention mechanism Gated attention mechanism Feature fusion Feature fusion
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Du, Yongping , Liu, Yang , Peng, Zhi et al. Gated attention fusion network for multimodal sentiment classification [J]. | KNOWLEDGE-BASED SYSTEMS , 2022 , 240 . |
MLA | Du, Yongping et al. "Gated attention fusion network for multimodal sentiment classification" . | KNOWLEDGE-BASED SYSTEMS 240 (2022) . |
APA | Du, Yongping , Liu, Yang , Peng, Zhi , Jin, Xingnan . Gated attention fusion network for multimodal sentiment classification . | KNOWLEDGE-BASED SYSTEMS , 2022 , 240 . |
Export to | NoteExpress RIS BibTex |
Abstract :
跨领域情感分类任务旨在利用富含情感标签的源域数据对缺乏标签的目标域数据进行情感极性分析.由此,文中提出基于对抗式分布对齐的跨域方面级情感分类模型,利用方面词与上下文的交互注意力学习语义关联,基于梯度反转层的领域分类器学习共享的特征表示.利用对抗式训练扩大领域分布的对齐边界,有效缓解模糊特征导致错误分类的问题.在Semeval-2014、Twitter数据集上的实验表明,文中模型性能较优.消融实验进一步表明捕获决策边界的模糊特征并扩大样本与决策边界间距离的策略可提高分类性能.
Keyword :
梯度反转 梯度反转 对抗式训练 对抗式训练 跨域方面级情感分析 跨域方面级情感分析 交互注意力 交互注意力
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 杜永萍 , 刘杨 , 贺萌 . 基于对抗式分布对齐的跨域方面级情感分析 [J]. | 模式识别与人工智能 , 2021 , 34 (1) : 87-94 . |
MLA | 杜永萍 et al. "基于对抗式分布对齐的跨域方面级情感分析" . | 模式识别与人工智能 34 . 1 (2021) : 87-94 . |
APA | 杜永萍 , 刘杨 , 贺萌 . 基于对抗式分布对齐的跨域方面级情感分析 . | 模式识别与人工智能 , 2021 , 34 (1) , 87-94 . |
Export to | NoteExpress RIS BibTex |
Abstract :
针对废旧手机回收过程中型号难以精确识别的问题,提出一种基于孪生卷积神经网络的废旧手机型号识别方法.首先,利用基于最大类间差分的边缘检测算法解析手机图像的区域特征,构建手机型号识别数据库;其次,构造一种共享权值孪生卷积网络(siamese convolutional neural network, S-CNN)的手机识别模型,实现废旧手机图像特征的快速提取;最后,设计一种自适应学习率的识别模型参数更新策略,提高手机型号识别的精度.将其应用于不同场景下废旧手机的分拣,实验结果表明该方法具有较好的快速性和准确性.
Keyword :
手机型号识别 手机型号识别 相似性评估 相似性评估 模型参数更新 模型参数更新 边缘检测 边缘检测 废旧手机回收 废旧手机回收 孪生卷积神经网络 孪生卷积神经网络
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 韩红桂 , 甄琪 , 任柯燕 et al. 基于孪生卷积神经网络的手机型号识别方法 [J]. | 北京工业大学学报 , 2021 , 47 (02) : 112-119 . |
MLA | 韩红桂 et al. "基于孪生卷积神经网络的手机型号识别方法" . | 北京工业大学学报 47 . 02 (2021) : 112-119 . |
APA | 韩红桂 , 甄琪 , 任柯燕 , 伍小龙 , 杜永萍 , 乔俊飞 . 基于孪生卷积神经网络的手机型号识别方法 . | 北京工业大学学报 , 2021 , 47 (02) , 112-119 . |
Export to | NoteExpress RIS BibTex |
Abstract :
用户对项目评分数据的稀疏性是影响推荐质量的主要因素之一,提出了融合评分数据和评论文本的深度学习模型,通过引入辅助信息缓解评分数据稀疏性的影响.利用评论文本可以获取用户的偏好信息和项目特征,而评分数据中又包含了用户和项目之间的潜在关联.现有的融合模型对评分数据的处理大多数都是采用矩阵分解方法,为了更好地利用评分数据中的有效信息,文中利用卷积神经网络处理评论文本,并引入注意力机制提取评论信息中具有代表性的评论,从而更好地表征用户偏好和项目特征.利用深度神经网络处理评分数据提取其中的深度特征,将特征进行融合来预测出用户对项目的评分.文中在Amazon数据集上进行验证,以均方误差MSE作为评价指标,结果表明所提出的模型优于多个优秀的基线模型.
Keyword :
评论文本 评论文本 推荐系统 推荐系统 深度学习 深度学习 评分矩阵 评分矩阵 注意力机制 注意力机制
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 王艳 , 彭治 , 杜永萍 . 融合评分矩阵和评论文本的深度学习推荐模型 [J]. | 计算机技术与发展 , 2021 , 31 (8) : 13-18 . |
MLA | 王艳 et al. "融合评分矩阵和评论文本的深度学习推荐模型" . | 计算机技术与发展 31 . 8 (2021) : 13-18 . |
APA | 王艳 , 彭治 , 杜永萍 . 融合评分矩阵和评论文本的深度学习推荐模型 . | 计算机技术与发展 , 2021 , 31 (8) , 13-18 . |
Export to | NoteExpress RIS BibTex |
Export
Results: |
Selected to |
Format: |