检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OEE-CFC: A dataset for Open Event Extraction from Chinese Financial Commentary

OEE-CFC: A Dataset for Open Event Extraction from Chinese Fi...

引用

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

作者： Wan, Qizhi Wan, Changxuan Hu, Rong Liu, Dexi Xu, Wenwu Xu, Kang Zou, Meihua Liu, Tao Yang, Jie Xiong, Zhenwei School of Computer and Artificial Intelligence Jiangxi University of Finance and Economics Jiangxi Key Laboratory of Data and Knowledge Engineering China

ISBN: (纸本)9798891761681

To meet application needs, event extraction has shifted from simple entities to unconventional entities serving as event arguments. However, current corpora with unconventional entities as event arguments are limited in event types and lack rich multi-events and shared arguments. Financial commentary not only describes the basic elements of an event but also states the background, scope, manner, condition, result, and tool used for the event, as well as the tense, intensity, and emotions of actions or state changes. Therefore, it is not suitable to develop event types that include only a few specific roles, as these cannot comprehensively capture the event's semantics. Also, there are affluent complex entities serving as event arguments, multiple events, and shared event arguments. To advance the practicality of event extraction technology, this paper first develops a general open event template from the perspective of understanding the meaning of events, aiming to comprehensively reveal useful information about events. This template includes 21 event argument roles, divided into three categories: core event roles, situational event roles, and adverbial roles. Then, based on the constructed event template, Chinese financial commentaries are collected and manually annotated to create a corpus OEE-CFC supporting open event extraction. This corpus includes 17,469 events, 44,221 arguments, 3,644 complex arguments, and 5,898 shared arguments. Finally, based on the characteristics of OEE-CFC, we design four types of prompts, and two models for event argument extraction are developed, with experiments conducted on the prompts. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A remote sensing work-flow recommendation algorithm based on logical structure

A remote sensing work-flow recommendation algorithm based on...

引用

2022 International Conference on Signal Processing, computer Networks, and Communications, SPCNC 2022

作者： Zuo, Xianyu Wu, Yaohua Liu, Yang Lin, Yinghao Zhang, Lei Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan University Kaifeng475001 China

ISBN: (纸本)9781510664616

With the development of remote sensing products towards the direction of civilianization and popularization, work-flow customization plays an important role in the production of remote sensing products. The traditional customized work-flow model has large time cost, complex operation and high requirements for professional knowledge. The work-flow recommendation system can improve the construction efficiency of remote sensing work-flow to some extent and assist users to design high-quality remote sensing work-flow models. However, most of the existing remote sensing work-flow modeling methods ignore the logical structure characteristics of the work-flow, leading to large errors in the calculation results of similarity. Difficult to make work-flow recommendations effectively. Therefore, this paper proposes a customized recommendation algorithm for remote sensing work-flow based on logical structure. By focusing on logical structure, the reliability of similarity calculation between work-flow is improved, so as to find similar work-flow to help users recommend the next modeling node. Firstly, the work-flow model needs to be preprocessed: the user converts the constructed work-flow model into a process structure tree by using Petri net workflow, and uses the path table generation algorithm based on logical structure to convert the model information into data information and store it in the database for subsequent data processing;Then the flow data in the flow tree set was converted into a path table according to certain rules, and then the longest common subsequence similarity of each data in the path table was calculated to obtain the similarity calculation results based on the logical structure characteristics, the most similar work-flow in the work-flow library is found and the recommendation is made for the user. The method proposed in this paper is evaluated experimentally on the real data set, in terms of recall, precision and F1-score, which shows that the method

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

On-Line System of Garbage Image-Orientated Intelligent Classification, Submission and Examination 20

On-Line System of Garbage Image-Orientated Intelligent Class...

引用

20th IEEE International Conference on e-Business engineering, ICEBE 2024

作者： Tian, Jiayin Wang, Yaozhi Liu, Jiaxin Chen, Yan School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China Xi'an Jiaotong University Shaanxi Key Lab of Big Data Knowledge Engineering Shaanxi Xi'an China School of Computer Science and Technology Xi'an Jiaotong University Xi'an Jiaotong University Shaanxi Key Lab of Big Data Knowledge Engineering Shaanxi Xi'an China

ISBN: (纸本)9798350365856

In a world brimming with new products continually, novel waste types are ubiquitous. This makes current image-based garbage classification systems difficult to perform well due to the long-tailed effects of distribution of garbage types, and necessitates an urgent and efficient garbage classification with abilities of detecting new and rare wastes and class-incremental learning for environmental sustainability. Therefore, we propose a framework of Online System of Garbage Image-Oriented Intelligent Classification, Submission, and Examination, facilitating the incremental garbage classification efforts. In which, to identify novel garbage effectively, we also introduced few-shot object detection method with two key algorithms: Two-Stage Object Detection Learning Algorithm and Dynamic Query-based Incremental Few-shot Learning Algorithm. Our experiment results show that Both outperform the current existing ones in dataset, MS COCO. Then, a strategy of Class-Incremental learning based Residual Network is proposed to meet the need of new waste class-incremental learning. The experimental results support our strategy. Finally, a prototype system employed the above algorithms and the strategy is described. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

CITE: Compact Interactive TransformEr for Multilingual Image Captioning 23

CITE: Compact Interactive TransformEr for Multilingual Image...

引用

6th International Conference on Image and Graphics Processing, ICIGP 2023

作者： Xu, Yueyuan Hu, Zhenzhen Zhou, Yuanen Hao, Shijie Hong, Richang Key Laboratory of Knowledge Engineering with Big Data School of Computer and Information Hefei University of Technology China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

ISBN: (纸本)9781450398572

Current state-of-the-art image captioning models generate captions in a single language, requiring a combination of multiple language specific models to build a multilingual image captioning system. However, as the number of supported languages increases, it leads to the parameters of the multilingual image captioning system grow linearly. To tackle this issue, we propose a single Compact Interactive TransformEr (CITE) model, which can describe an image in multiple languages simultaneously, making the captioning system more compact. Specifically, based on the standard Transformer model, we share the encoder and decoder backbone parameters and replace the self-attention sub-layer in the decoder with the interactive attention sub-layer. In addition, we extend the traditional monolingual reinforcement learning mechanism to a multilingual version to promote better description generation. Due to the wide use of Chinese and English, we evaluate the performance of our CITE model by simultaneously generating English and Chinese captions. We expand the image captions of the whole MSCOCO dataset and release a COCO-EN-CN dataset. Extensive experiments on the COCO-EN-CN dataset show that our single CITE model with more parameter-efficient can maintain the competitive performance or even better than the monolingual captioning models. © 2023 ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Image Matching Algorithm Under Adverse Conditions Based on SIFT 14

Image Matching Algorithm Under Adverse Conditions Based on S...

引用

14th International Conference on information Technology in Medicine and Education, ITME 2024

作者： Chen, Hao Cao, Xinrong Li, Zuoyong Lin, Lihui Fuzhou University College of Computer and Big Data Fuzhou350108 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Fuzhou350121 China Wuyi University Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry School of Mathematics and Computer Science Fujian354300 China

ISBN: (纸本)9798350356670

Image matching technology is crucial in computer vision applications. However, the traditional SIFT (Scale-Invariant Feature Transform) algorithm often faces challenges under adverse conditions, such as a high number of mismatched points and few accurately matched points. Additionally, in practical scenarios, environmental factors like lighting changes and image blurring further reduce image similarity. Therefore, this paper proposes an improved SIFT-based image matching algorithm to address these challenges. First, SIFT is used to extract image features, and a bidirectional FLANN (Fast Library for Approximate Nearest Neighbors) matching strategy is employed to initially filter out incorrect features. Then, the RANSAC (Random Sample Consensus) algorithm is used to screen out unreliable matching point pairs. Finally, the matching accuracy is evaluated based on the remaining pure matching point pairs. Experimental results demonstrate that, compared to the traditional SIFT algorithm, this improved algorithm achieves higher matching accuracy and robustness under adverse conditions, exhibiting superior performance. © 2024 IEEE.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

Rating Text Classification with Weighted Negative Supervision on Classifier Layer

引用

Chinese Journal of Electronics 2023年第6期32卷 1304-1318页

作者： ZHANG Jun QIU Longlong SHEN Fanfan HE Yueshun TAN Hai HE Yanxiang Radiological Geosciences Big Data Engineering Laboratory of Jiangxi Province East China University of Technology School of Information Engineering East China University of Technology School of Computer Science Nanjing Audit University Computer School Wuhan University

Bidirectional encoder representations from transformers(BERT) gives full play to the advantages of the attention mechanism, improves the performance of sentence representation, and provides a better choice for various natural language understanding(NLU)tasks. Many methods using BERT as the pre-trained model achieve state-of-the-art performance in almost various text classification scenarios. Among them, the multitask learning framework combining the negative supervision and the pre-trained model solves the issue of the model performance degradation that occurs as the semantic similarity of texts conflicts with the classification standards. The current model does not consider the degree of difference between labels, which leads to insufficient difference information learned by the model, and affects classification performance, especially in the rating classification tasks. On the basis of the multi-task learning model, this paper fully considers the degree of difference between labels, which is expressed by using weights to solve the above problems. We supervise negative samples on the classifier layer instead of the encoder layer, so that the classifier layer can also learn the difference information between the labels. Experimental results show that our model can not only performs well in 2-class and multi-class rating text classification tasks, but also performs well in different languages.

关键词： Training Text categorization Semantics Bidirectional control Transformers Multitasking Encoding

来源：评论

学校读者我要写书评

暂无评论

Stable Learning via Triplex Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5267-5276页

作者： Yang, Shuai Jiang, Tingting Dang, Qianlong Gu, Lichuan Wu, Xindong Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing Hefei230036 China Northwest A & F University College of Science Yangling712100 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

Stable learning aims to learn a model that generalizes well to arbitrary unseen target domain by leveraging a single source domain. Recent advances in stable learning have focused on balancing the distribution of confounders for each feature to eliminate spurious correlations. However, previous studies treat all features equally without considering the difficulties of confounder balancing associated with different features, and regard irrelevant features as confounders, deteriorating generalization performance. To tackle these issues, this article proposes a novel triplex learning (TriL) based stable learning algorithm, which performs sample reweighting, causal feature selection, and representation learning to remove spurious correlations. Specifically, first, TriL adaptively assigns weights to the confounder balancing term of each feature in accordance with the difficulties of confounder balancing, and aligns the confounder distribution of each feature by learning a group of sample weights. Second, TriL integrates the sample weights into a weighted cross-entropy model to compute causal effects of features for excluding irrelevant features from the confounder set. Finally, TriL relearns a set of sample weights and uses them to guide a new supervised dual-autoencoder containing two classifiers to learn feature representations. TriL forces the results of two classifiers to remain consistent for removing spurious correlations by using a cross-classifier consistency regularization. Extensive experiments on synthetic and two real-world datasets show the superiority of TriL compared with seven methods. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

HUSS:A Heuristic Method for Understanding the Semantic Structure of Spreadsheets

引用

data Intelligence 2023年第3期5卷 537-559页

作者： Xindong Wu Hao Chen Chenyang Bu Shengwei Ji Zan Zhang Victor S.Sheng Key Laboratory of Knowledge Engineering with Big Data(the Ministry of Education of China) Hefei University of TechnologyChinaSchool of Computer Science and Information EngineeringHefei University of TechnologyHefeiChina Research Institute of Artificial Intelligence Zhejiang LabHangzhouChina Department of Computer Science Texas Tech UniversityLubbockTX 79409USA

Spreadsheets contain a lot of valuable data and have many practical *** key technology of these practical applications is how to make machines understand the semantic structure of spreadsheets,e.g.,identifying cell function types and discovering relationships between cell *** existing methods for understanding the semantic structure of spreadsheets do not make use of the semantic information of cells.A few studies do,but they ignore the layout structure information of spreadsheets,which affects the performance of cell function classification and the discovery of different relationship types of cell *** this paper,we propose a Heuristic algorithm for Understanding the Semantic Structure of spreadsheets(HUSS).Specifically,for improving the cell function classification,we propose an error correction mechanism(ECM)based on an existing cell function classification model[11]and the layout features of *** improving the table structure analysis,we propose five types of heuristic rules to extract four different types of cell pairs,based on the cell style and spatial location *** experimental results on five real-world datasets demonstrate that HUSS can effectively understand the semantic structure of spreadsheets and outperforms corresponding baselines.

关键词： Spreadsheet semantic structure information extraction Heuristics Cell function analysis Table structure analysis

来源：评论

学校读者我要写书评

暂无评论

A Low-Rank Matching Attention Based Cross-Modal Feature Fusion Method for Conversational Emotion Recognition

引用

IEEE Transactions on Affective Computing 2024年第02期16卷 1177-1189页

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo Xi'An Jiaotong School of Computer Science and Technology Ministry of Education Key Laboratory for Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi'an710049 China Xi'An Jiaotong School of Computer Science and Technology Shaanxi Xi'an710049 China BigKEJoint Innovation Center SHMEEA Shanghai China Xi'An Jiaotong University School of Mathematics and Statistics Xi'an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. © 2024 IEEE.

关键词： Semantics

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：