检索结果-内蒙古大学图书馆

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

作者： Ou, Yimin Jian, Ping School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Institute of Technology Beijing China

ISBN: (纸本)9782493814104

Diffusion models have become a powerful generative modeling paradigm, achieving great success in continuous data patterns. However, the discrete nature of text data results in compatibility issues between continuous diffusion models (CDMs) and pre-trained language models (PLMs). That is, the performance of diffusion models even degrades when combined with PLMs. To alleviate this issue, we propose to utilize a pre-trained decoder to convert the denoised embedding vectors into natural language instead of using the widely used rounding operation. In this way, CDMs can be more effectively combined with PLMs. Additionally, considering that existing noise schedules in text diffusion models do not take into account the linguistic differences among tokens, which violates the easy-first policy for text generation, we propose a linguistic easy-first schedule that incorporates the measure of word importance, conforming to easy-first-generation linguistic features and bringing about improved generation quality. Experiment results on the E2E dataset and five controllable tasks show that our approach can combine the merits of CDMs and PLMs, significantly outperforming other diffusion-based models. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Improving Implicit Discourse Relation Recognition with Semantics Confrontation 30

Improving Implicit Discourse Relation Recognition with Seman...

引用

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

作者： Cai, Mingyang Yang, Zhen Jian, Ping School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Institute of Technology Beijing China

ISBN: (纸本)9782493814104

Implicit Discourse Relation Recognition (IDRR), which infers discourse logical relations without explicit connectives, is one of the most challenging tasks in natural language processing (NLP). Recently, pre-trained language models (PLMs) have yielded impressive results across numerous NLP tasks, but their performance still remains unsatisfactory in IDRR. We argue that prior studies have not fully harnessed the potential of PLMs, thereby resulting in a mixture of logical semantics, which determine the logical relations between discourse arguments, and general semantics, which encapsulate the non-logical contextual aspects (detailed in Sec.1). Such a mixture would inevitably compromise the logic reasoning ability of PLMs. Therefore, we propose a novel method that trains the PLMs through two semantics enhancers to implicitly differentiate logical and general semantics, ultimately achieving logical semantics enhancement. Due to the characteristic of PLM in word representation learning, these two semantics enhancers will inherently confront with each other, facilitating an augmentation of logical semantics by disentangling them from general semantics. The experimental results on PDTB 2.0 dataset show that the confrontation approach exceeds our baseline by 3.81% F1 score, and the effectiveness of the semantics confrontation method is validated by comprehensive ablation experiments. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Category-Aware Test-Time Training Domain Adaptation

Category-Aware Test-Time Training Domain Adaptation

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Yangqin Feng Xinxing Xu Huazhu Fu Yan Wang Zizhou Wang Liangli Zhen Rick Siow Mong Goh Yong Liu Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

Machine learning models often struggle to generalise to out-of-distribution (OOD) data. One promising solution for solving this problem is test-time training domain adaptation, which adjusts a trained model to the new test data without revisiting the source dataset, thus preserving the privacy of source data. However, existing test-time training methods have not considered the mining of category information of the test data in the training for domain adaptation, thus suffering in inaccurate domain alignment. In this paper, we propose a novel method called category-aware test-time training (CAT 3 ) to adapt the pre-trained model to test data on the fly. CAT 3 first trains a model with multiple diverse classifiers using the source datasets and conducts a source data summarisation. Then, it assigns the pseudo-labels for the test data that have consistent classification results from the trained classifiers and adjusts the pre-trained model by aligning these reliable test data to their corresponding source data categories iteratively. Unlike existing test-time training methods, CAT 3 reveals the category information of the test data and aligns these reliable test data to the source data at the category level instead of the dataset level. Empirical results demonstrate that CAT 3 can outperform the current state-of-the-art methods on several benchmarks, indicating our proposed method’s effectiveness.

关键词： Training Adaptation models Data privacy Correlation Machine learning Learning (artificial intelligence) Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Llama-TCR: Generate De Novo TCR with Large Language Model

Llama-TCR: Generate De Novo TCR with Large Language Model

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Jun Zhou Zhenzhou Wu Mengren Man Yonghui Wu Le Dinh Linh Manna Dai Yong Liu Rick Goh Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

T cell receptor-engineered T cell (TCR-T), where T cells are equipped with engineered antigen-specific receptors, is a promising approach of cancer immunotherapy. However, it is known that naturally occurred TCR is not able to detect some cancer antigens due to negative selection and resulted in the proliferation of cancer cells. This study introduces a novel application of large language models (LLM) in the de novo generation of T cell receptors (TCR). We propose Llama-TCR, a generative model trained on database of antigen and TCR pairs, for diverse and functional candidate TCR sequence generation. Using both sequence based benchmarking and 3D structure inspection, we show that the model is able to generate TCR sequences targeting to given antigens and has great potential in the development of novel TCR-T immunotherapy.

关键词： Antigens Visualization Solid modeling Three-dimensional displays Large language models Immunotherapy Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Data Heterogeneity Evaluation Approaches for Personalized Federated Learning

Benchmarking Data Heterogeneity Evaluation Approaches for P...

引用

International Workshop on Trustworthy Federated Learning, FL 2024

作者： Li, Zhilong Wu, Xiaohu Tang, Xiaoli He, Tiantian Ong, Yew-Soon Chen, Mengmeng Liu, Qiqi Lao, Qicheng Yu, Han Beijing University of Posts and Telecommunications Beijing China College of Computing and Data Science Nanyang Technological University Singapore Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore Singapore Centre for Frontier AI Research Agency for Science Technology and Research Singapore Singapore School of Engineering Westlake University Hangzhou China

ISBN: (纸本)9783031822391

There is growing research interest in measuring the statistical heterogeneity of clients’ local datasets. Such measurements are used to estimate the suitability for collaborative training of personalized federated learning (PFL) models. Currently, these research endeavors are taking place in silos and there is a lack of a unified benchmark to provide a fair and convenient comparison among various approaches in common settings. We aim to bridge this important gap in this paper. The proposed benchmarking framework currently includes six representative approaches. Extensive experiments have been conducted to compare these approaches under five standard non-IID FL settings, providing much needed insights into which approaches are advantageous under which settings. The proposed framework offers useful guidance on the suitability of various data divergence measures in FL systems. It is beneficial for keeping related research activities on the right track in terms of: (1) designing PFL schemes, (2) selecting appropriate data heterogeneity evaluation approaches for specific FL application scenarios, and (3) addressing fairness issues in collaborative model training. The code is available at https://***/Xiaoni-61/DH-Benchmark. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Using Graph Attention Network to Reversely Design GaN MIS-HEMTs Based on Hand-Drawn Characteristics

引用

IEEE Access 2023年 11卷 70168-70173页

作者： Tseng, Yi-Ming Chen, Bang-Ren Lin, Wei-Cheng Lee, Wen-Jay Chen, Nan-Yow Wu, Tian-Li National Yang Ming Chiao Tung University International College of Semiconductor Technology Hsinchu30010 Taiwan Institute of Electronics National Yang Ming Chiao Tung University Hsinchu30010 Taiwan National Center for High-Performance Computing Hsinchu30076 Taiwan

In this work, the methodology using Graph Attention Network (GAT) for the reserve design in GaN power MIS-HEMTs based on hand-drawn characteristics is demonstrated for the first-time. The hand-drawn ID-VG characteristic is constructed by Ramer-Douglas-Peucker algorithm. Then, the extracted information is sent to the Graph Attention Network to receive the corresponding device design variables, including tAlGaN, recessed depth, Al%, Lg, Lgd, and Lgs. Less than 30 seconds is consumed to generate the design variables and less than 8% of the differences in the key extracted parameters, such as threshold voltage (Vth), On-state current (Ion), and subthreshold slope (SS), can be achieved by comparing hand-drawn ID-VG and simulated ID-VG characteristic based on the design variables from GAT model. Therefore, the developed GAT approach is promising for the reverse design of GaN power MIS-HEMTs, which can provide users with efficient and valuable design suggestions to optimize the devices toward the targeting performance. © 2013 IEEE.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

TaiwanVQA: A Benchmark for Visual Question Answering for Taiwanese Daily Life 1

TaiwanVQA: A Benchmark for Visual Question Answering for Tai...

引用

1st Workshop of Evaluation of Multi-Modal Generation, EvalMG 2025

作者： Hsieh, Hsin-Yi Liu, Shang-Wei Meng, Chih-Chang Chen, Chien-Hua Lin, Shuo-Yueh Lin, Hung-Ju Huang, Hen-Hsen Chen Wu, I. National Center for High-performance Computing Taiwan National Central University Taiwan National Yang Ming Chiao Tung University Taiwan National Taiwan University Taiwan Institute of Information Science Academia Sinica Taiwan

ISBN: (纸本)9798891762138

We introduce TaiwanVQA, a novel visual question answering benchmark designed to evaluate vision language models’ (VLMs) ability to recognize and reason about Taiwan-specific multimodal content. TaiwanVQA comprises 2,000 image-question pairs covering diverse topics relevant to Taiwanese culture and daily life. We categorize the questions into recognition and reasoning tasks, further sub-classifying reasoning questions based on the level of external knowledge required. We conduct extensive experiments on state-of-the-art VLMs, including GPT-4o, Llama-3.2, LLaVA, Qwen2-VL, and InternVL2 models. Our findings reveal significant limitations in current VLMs when handling culturally specific content. The performance gap widens between recognition tasks (top score 73.60%) and reasoning tasks (top score 49.80%), indicating challenges in cultural inference and contextual understanding. These results highlight the need for more culturally diverse training data and improved model architectures that can better integrate visual and textual information within specific cultural contexts. By providing TaiwanVQA, we aim to contribute to the development of more inclusive and culturally aware AI models, facilitating their deployment in diverse real-world settings. TaiwanVQA can be accessed on our GitHub page. © 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

PIOD: An Efficient Parallel Iterative Algorithm for Solving Over-determined Equations 29

PIOD: An Efficient Parallel Iterative Algorithm for Solving ...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Tian, Min Wei, Zhenguo Li, Yanlong Du, Wei Xiao, Lei Xu, Chaoshuai China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks China Jinan Institute of Supercomputing Technology Jinan Key Laboratory of High Performance Computing China

ISBN: (纸本)9798350330717

The solution of over-determined equations plays a very important role in fields such as data fitting, signal processing, and machine learning. It is of great significance in predicting natural phenomena, optimizing engineering design, and other fields. However, there is currently no efficient method to solve over-determined equations, either being not accurate enough or consuming a lot of time. In this article, we propose a parallel iterative method for solving over-determined equations, called the PIOD algorithm. By using a sub-convergence condition to terminate the iterative calculation, we have developed a task partitioning strategy for the algorithm and implemented parallelization of the solution of over-determined equations on a distributed memory system. Our proposed algorithm achieves an average speedup of 152 ×times compared to the open-source Eigen solver. Additionally, it also achieves a parallel efficiency of over 30%. © 2023 IEEE.

关键词： conjugate gradient method MPI over-determined equations parallel algorithms parallel iterative methods

来源：评论

学校读者我要写书评

暂无评论

Degenerate polarization entangled photon source based on a single Ti-diffusion lithium niobate waveguide in a polarization Sagnac interferometer

引用

Chinese Physics B 2023年第8期32卷 69-73页

作者：孙宇孙昌伟周唯杨然端家晨龚彦晓徐平祝世宁 National Laboratory of Solid State Microstructures and School of Physics Nanjing UniversityNanjing 210093China NanZhi Institude of Advanced Optoelectronic Integration Nanjing 210018China Institute for Quantum Information and State Key Laboratory of High Performance Computing College of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410073China

Combining a Ti-diffusion periodically poled lithium niobate(PPLN)waveguide with a Sagnac interferometer,two opposite directions type-II spontaneous parametric down conversions(SPDC)occur coherently and yield a high brightness,high stability polarization entanglement *** source produces degenerate photon pairs at 1540.4 nm with a brightness of B=(1.36±0.03)×10^(6) pairs/(s·nm·m W).We perform quantum state tomography to reconstruct the density matrix of the output state and obtain a fidelity of F=0.983±*** high brightness and phase stability of our waveguide source enable a wide range of quantum information experiments operating at a low pump power as well as hold the advantage in mass production which can promote the practical applications of quantum technologies.

关键词： polarization entanglement source Sagnac interferometer quantum information lithium niobate waveguide

来源：评论

学校读者我要写书评

暂无评论

Dependency-Type Weighted Graph Convolutional Network on End-to-End Aspect-Based Sentiment Analysis 13th

Dependency-Type Weighted Graph Convolutional Network on End...

引用

13th IFIP TC 12 International Conference on Intelligent Information Processing, IIP 2024

作者： Mu, Yusong Shi, Shumin School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China

ISBN: (纸本)9783031579189

Previous studies consider little on using dependency-type messages in the E2E-ABSA task. Studies using dependency-type messages just contact the dependency-type message and word embedding vectors, which may not fully fuse the context feature and information from the dependency type. This paper proposes a new model called Dependency-Type Weighted Graph Convolution Network (DTW-GCN) to compose dependency-type messages and word embedding. We use a type-weighted matrix to combine the dependency-type message, and DTW-GCN could fuse the dependency-type message and word embedding vectors. Experiments conducted on three benchmark datasets verify the effectiveness of our model. © IFIP International Federation for Information Processing 2024.

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：