检索结果-内蒙古大学图书馆

44th ACM/IEEE International Conference on Software Engineering, ICSE 2024

作者： Du, Xueying Liu, Mingwei Wang, Kaixin Wang, Hanlin Liu, Junwei Chen, Yixuan Feng, Jiayi Sha, Chaofeng Peng, Xin Lou, Yiling School of Computer Science and Shanghai Key Laboratory of Data Science Fudan University China Fudan University Shanghai China

ISBN: (纸本)9798400702174

Recently, many large language models (LLMs) have been proposed, showing advanced proficiency in code generation. Meanwhile, many efforts have been dedicated to evaluating LLMs on code generation benchmarks such as HumanEval. Although being very helpful for comparing different LLMs, existing evaluation focuses on a sim-ple code generation scenario (i.e., function-level or statement-level code generation), which mainly asks LLMs to generate one single code unit (e.g., a function or a statement) for the given natural language description. Such evaluation focuses on generating independent and often small-scale code units, thus leaving it unclear how LLMs perform in real-world software development scenarios. To fill this knowledge gap, we make the first attempt to evaluate LLMs in a more challenging code generation scenario, i.e., class-level code generation. Compared with existing code generation benchmarks, it better reflects real-world software development scenarios due to it comprising broader contextual dependencies and multiple, interdependent units of code. We first manually construct the first class-level code generation benchmark ClassEval of 100 class-level Python code generation tasks with approximately 500 person-hours. Based on the new benchmark ClassEval, we then perform the first study of 11 state-of-the-art LLMs on class-level code generation. Based on our results, we find that all LLMs perform much worse on class-level code generation compared to the method-level. While GPT models still dominate other LLMs on class-level code generation, the performance rankings of other models on method-level code generation no longer holds for class-level code generation. Besides, most models (except GPT models) perform better when generating the class method by method;and they have the limited ability of generating dependent code. Based on our findings, we call for software engineering (SE) researchers' expertise to build more LLM benchmarks based on practical and com

关键词： Function evaluation

来源：评论

学校读者我要写书评

暂无评论

Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding

Reason from Fallacy: Enhancing Large Language Models' Logica...

引用

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Li, Yanda Wang, Dixuan Liang, Jiaqing Jiang, Guochao He, Qianyu Xiao, Yanghua Yang, Deqing School of Data Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science Shanghai China

ISBN: (纸本)9798891761193

Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but they still struggle with some complicated reasoning tasks including logical reasoning. One non-negligible reason for LLMs' suboptimal performance on logical reasoning is their overlooking of understanding logical fallacies correctly. To evaluate LLMs' capability of logical fallacy understanding (LFU), we propose five concrete tasks from three cognitive dimensions of WHAT, WHY, and HOW in this paper. Towards these LFU tasks, we have successfully constructed a new dataset LFUD based on GPT-4 accompanied by a little human effort. Our extensive experiments justify that our LFUD can be used not only to evaluate LLMs' LFU capability, but also to fine-tune LLMs to obtain significantly enhanced performance on logical reasoning. © 2024 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

Chinese Named Entity Recognition Augmented with Lexicon Memory

引用

Journal of computer science & Technology 2023年第5期38卷 1021-1035页

作者：周奕郑骁庆黄萱菁 School of Computer Science Fudan UniversityShanghai 200438China Shanghai Key Laboratory of Intelligent Information Processing Shanghai 200438China

Inspired by the concept of content-addressable retrieval from cognitive science,we propose a novel fragment-based Chinese named entity recognition(NER)model augmented with a lexicon-based memory in which both character-level and word-level features are combined to generate better feature representations for possible entity *** that the boundary information of entity names is particularly useful to locate and classify them into pre-defined categories,position-dependent features,such as prefix and suffix,are introduced and taken into account for NER tasks in the form of distributed *** lexicon-based memory is built to help generate such position-dependent features and deal with the problem of out-of-vocabulary *** results show that the proposed model,called LEMON,achieved state-of-the-art performance with an increase in the Fl-score up to 3.2%over the state-of-the-art models on four different widely-used NER datasets.

关键词： named entity recognition(NER) lexicon-based memory content-addressable retrieval position-dependent feature neural network

来源：评论

学校读者我要写书评

暂无评论

XMeCap: Meme Caption Generation with Sub-Image Adaptability 24

XMeCap: Meme Caption Generation with Sub-Image Adaptability

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Chen, Yuyan Yan, Songzhou Zhu, Zhihong Li, Zhixu Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China Peking University Beijing China

ISBN: (纸本)9798400706868

Humor, deeply rooted in societal meanings and cultural details, poses a unique challenge for machines. While advances have been made in natural language processing, real-world humor often thrives in a multi-modal context, encapsulated distinctively by memes. This paper poses a particular emphasis on the impact of multi-images on meme captioning. After that, we introduce the XMeCap framework, a novel approach that adopts supervised fine-tuning and reinforcement learning based on an innovative reward model, which factors in both global and local similarities between visuals and text. Our results, benchmarked against contemporary models, manifest a marked improvement in caption generation for both single-image and multi-image memes, as well as different meme categories. XMeCap achieves an average evaluation score of 75.85 for single-image memes and 66.32 for multi-image memes, outperforming the best baseline by 3.71% and 4.82%, respectively. This research not only establishes a new frontier in meme-related studies but also underscores the potential of machines in understanding and generating humor in a multi-modal setting. © 2024 ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Seeking a Sense of Meaning and Companionship in Life: Informal Learning on Douyin Among Chinese Older Adults

引用

Proceedings of the ACM on Human-computer Interaction 2025年第2期9卷 1-24页

作者： Qian, Zhigu Fu, Jiaojiao Zhou, Yangfan School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing China School of Information Science and Engineering East China University of Science and Technology China

This study examines how Chinese older adults leverage Douyin, a short video platform, for informal learning purposes, analyzing their usage patterns, motivations, and encountered challenges. Although Douyin was not explicitly designed with educational features, it has emerged as a significant informal learning platform for this demographic. Through a qualitative investigation comprising participant observations and semi-structured interviews with 17 participants, we reveal the distinctive learning experience that Douyin facilitates. The platform’s unique combination of short-form videos, live streaming capabilities, and interactive community features creates an engaging learning environment that particularly resonates with older adults. Our findings demonstrate that participants derive substantial social-emotional benefits beyond knowledge acquisition, including strengthened social connections, enhanced companionship, and a reinforced sense of purpose through their Douyin engagement. These social-emotional aspects emerge as crucial factors driving older adults’ selection of Douyin as their preferred learning platform. By providing comprehensive insights into older adults’ engagement with digital platforms for lifelong learning, this research offers valuable implications for HCI, particularly in understanding how technology can be optimized to support the learning needs of older populations. © 2025 Association for Computing Machinery. All rights reserved.

关键词： Social aspects

来源：评论

学校读者我要写书评

暂无评论

Prediction of three-dimensional ocean temperature in the South China Sea based on time series gridded data and a dynamic spatiotemporal graph neural network

引用

Acta Oceanologica Sinica 2024年第7期43卷 26-39页

作者： Feng Nan Zhuolin Li Jie Yu Suixiang Shi Xinrong Wu Lingyu Xu Department of Computer Engineering and Science Shanghai UniversityShanghai 200444China Key Laboratory of Digital Ocean National Marine Data and Information ServiceTianjin 300171China

Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related ***,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean *** graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among *** this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior *** and spatial dependencies in the time series were then captured using temporal and graph *** also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid *** this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea *** compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.

关键词： dynamic associations three-dimensional ocean temperature prediction graph neural network time series gridded data

来源：评论

学校读者我要写书评

暂无评论

Multi-scale feature fusion for facial expression recognition

引用

Neural Computing and Applications 2025年 1-22页

作者： Guo, Jiatao Peng, Junjie Huang, Yansong Chen, Gan Cai, Zesu Tan, Shuhua School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China School of Computer Science and Technology Harbin Institute of Technology Harbin China National Engineering Laboratory for Logistics Information Technology YTO Express Co. Ltd. Shanghai China

As an important computer vision task that can be used in many areas, facial expression recognition (FER) has been widely studied which much progress has been obtained especially when deep learning (DL) approaches have been introduced in FER. However, existing methods are restricted to extracting localized information or utilizing attention mechanism to focus on the region most relevant to the emotion, possibly resulting in errors in facial expression interpretation. Moreover, the inconsistency of image sizes in the wild FER datasets further increases the difficulty of the FER task. To address these issues, we propose a multi-scale feature fusion (MSFF) for FER. Specifically, our method first extracts features from facial images using multi-scale feature extraction to obtain rich multi-dimensional information. Meanwhile, extensive feature extraction at different scales is achieved by expanding the receptive field of the model, which provides the basis for more detailed analysis of facial expressions. Eventually, features at different scales are fused to enhance their synergistic effect. Subsequently, the adaptive extraction of comprehensive and valuable information from the fused features is performed, optimizing the performance of expression recognition. Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art methods on in-the-wild datasets. It is promising for FER in realistic and complex scenarios. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

ToNER: Type-oriented Named Entity Recognition with Generative Language Model 30

ToNER: Type-oriented Named Entity Recognition with Generativ...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Jiang, Guochao Luo, Ziqin Shi, Yuchen Wang, Dixuan Liang, Jiaqing Yang, Deqing School of Data Science Fudan University China Shanghai Key Laboratory of Data Science China

ISBN: (纸本)9782493814104

In recent years, the fine-tuned generative models have been proven more powerful than the previous tagging-based or span-based models on named entity recognition (NER) task. It has also been found that the information related to entities, such as entity types, can prompt a model to achieve NER better. However, it is not easy to determine the entity types indeed existing in the given sentence in advance, and inputting too many potential entity types would distract the model inevitably. To exploit entity types' merit on promoting NER task, in this paper we propose a novel NER framework, namely ToNER based on a generative model. In ToNER, a type matching model is proposed at first to identify the entity types most likely to appear in the sentence. Then, we append a multiple binary classification task to fine-tune the generative model's encoder, so as to generate the refined representation of the input sentence. Moreover, we add an auxiliary task for the model to discover the entity types which further fine-tunes the model to output more accurate results. Our extensive experiments on some NER benchmarks verify the effectiveness of our proposed strategies in ToNER that are oriented towards entity types' exploitation. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

TopicBubbler:An interactive visual analytics system for cross-level fine-grained exploration of social media data

引用

Visual Informatics 2023年第4期7卷 41-56页

作者： Jielin Feng Kehao Wu Siming Chen School of Data Science Fudan UniversityChina Faculty of Engineering The University of SydneyAustralia Shanghai Key Laboratory of Data Science China

How to explore fine-grained but meaningful information from the massive amount of social media data is critical but *** address this challenge,we propose the TopicBubbler,a visual analytics system that supports the cross-level fine-grained exploration of social media *** achieve the goal of cross-level fine-grained exploration,we propose a new *** the procedure of the workflow,we construct the fine-grained exploration view through the design of bubble-based word *** bubble contains two rings that can display information through different levels,and recommends six keywords computed by different *** view supports users collecting information at different levels and to perform fine-grained selection and exploration across different levels based on keyword *** enable the users to explore the temporal information and the hierarchical structure,we also construct the Temporal View and Hierarchical View,which satisfy users to view the cross-level dynamic trends and the overview hierarchical *** addition,we use the storyline metaphor to enable users to consolidate the fragmented information extracted across levels and topics and ultimately present it as a complete *** studies from real-world data confirm the capability of the TopicBubbler from different perspectives,including event mining across levels and topics,and fine-grained mining of specific topics to capture events hidden beneath the surface.

关键词： Cross level analysis Fine grained exploration Topic analysis Social media

来源：评论

学校读者我要写书评

暂无评论

Space Complexity of Euclidean Clustering

引用

IEEE Transactions on Information Theory 2025年第6期71卷 4515-4536页

作者： Zhu, Xiaoyi Tian, Yuxiang Huang, Lingxiao Huang, Zengfeng Fudan University School of Data Science Shanghai200433 China Nanjing University State Key Laboratory of Novel Software Technology New Cornerstone Science Laboratory Nanjing210023 China

The (k, z)-Clustering problem in Euclidean space Rd has been extensively studied. Given the scale of data involved, compression methods for the Euclidean (k, z)-Clustering problem, such as data compression and dimension reduction, have received significant attention in the literature. However, the space complexity of the clustering problem, specifically, the number of bits required to compress the cost function within a multiplicative error ϵ, remains unclear in existing literature. This paper initiates the study of space complexity for Euclidean (k, z)-Clustering and offers both upper and lower bounds. Our space bounds are nearly tight when k is constant, indicating that storing a coreset, a well-known data compression approach, serves as the optimal compression scheme. Furthermore, our lower bound result for (k, z)-Clustering establishes a tight space bound of Θ(nd) for terminal embedding, where n represents the dataset size. Our technical approach leverages new geometric insights for principal angles and discrepancy methods, which may hold independent interest. © 1963-2012 IEEE.

关键词： Cost functions

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：