检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Wei, Jiyao Guan, Saiping Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9798891761964

N-ary Knowledge Graphs (NKGs), where a fact can involve more than two entities, have gained increasing attention. Link Prediction in NKGs (LPN) aims to predict missing elements in facts to facilitate the completion of NKGs. Current LPN methods implicitly operate under a closed-world assumption, meaning that the sets of entities and roles are fixed. These methods focus on predicting missing elements within facts composed of entities and roles seen during training. However, in reality, new facts involving unseen entities and roles frequently emerge, requiring completing these facts. Thus, this paper proposes a new task, Inductive Link Prediction in NKGs (ILPN), which aims to predict missing elements in facts involving unseen entities and roles in emerging NKGs. To address this task, we propose a Meta-learning-based Nary knowledge Inductive Reasoner (MetaNIR), which employs a graph neural network with meta-learning mechanisms to embed unseen entities and roles adaptively. The obtained embeddings are used to predict missing elements in facts involving unseen elements. Since no existing dataset supports this task, three datasets are constructed to evaluate the effectiveness of MetaNIR. Extensive experimental results demonstrate that MetaNIR consistently outperforms representative models across all datasets. © 2025 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Classifier Guidance Enhances Diffusion-Based Adversarial Purification by Preserving Predictive Information 27

Classifier Guidance Enhances Diffusion-Based Adversarial Pur...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Zhang, Mingkun Li, Jianing Chen, Wei Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781643685489

Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image classification tasks. However, such methods fall into the dilemma of balancing the needs for noise removal and information preservation. This paper points out that existing adversarial purification methods based on diffusion models gradually lose sample information during the core denoising process, causing occasional label shift in subsequent classification tasks. As a remedy, we suggest to suppress such information loss by introducing guidance from the classifier confidence. Specifically, we propose Classifier-cOnfidence gUided Purification (COUP) algorithm, which purifies adversarial examples while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods. © 2024 The Authors.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Selective Temporal Knowledge Graph Reasoning 30

Selective Temporal Knowledge Graph Reasoning

引用

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

作者： Hou, Zhongni Jin, Xiaolong Li, Zixuan Bai, Long Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9782493814104

Temporal Knowledge Graph (TKG), which characterizes temporally evolving facts in the form of (subject, relation, object, timestamp), has attracted much attention recently. TKG reasoning aims to predict future facts based on given historical ones. However, existing TKG reasoning models are unable to abstain from predictions they are uncertain, which will inevitably bring risks in real-world applications. Thus, in this paper, we propose an abstention mechanism for TKG reasoning, which helps the existing models make selective, instead of indiscriminate, predictions. Specifically, we develop a confidence estimator, called Confidence Estimator with History (CEHis), to enable the existing TKG reasoning models to first estimate their confidence in making predictions, and then abstain from those with low confidence. To do so, CEHis takes two kinds of information into consideration, namely, the certainty of the current prediction and the accuracy of historical predictions. Experiments with representative TKG reasoning models on two benchmark datasets demonstrate the effectiveness of the proposed CEHis. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Few-shot Link Prediction on Hyper-relational Facts 30

Few-shot Link Prediction on Hyper-relational Facts

引用

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

作者： Wei, Jiyao Guan, Saiping Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9782493814104

Hyper-relational facts, which consist of a primary triple (head entity, relation, tail entity) and auxiliary attribute-value pairs, are widely present in real-world Knowledge Graphs (KGs). Link Prediction on Hyper-relational Facts (LPHFs) is to predict a missing element in a hyper-relational fact, which helps populate and enrich KGs. However, existing LPHFs studies usually require an amount of high-quality data. They overlook few-shot relations, which have limited instances, yet are common in real-world scenarios. Thus, we introduce a new task, Few-Shot Link Prediction on Hyper-relational Facts (FSLPHFs). It aims to predict a missing entity in a hyper-relational fact with limited support instances. To tackle FSLPHFs, we propose MetaRH, a model that learns Meta Relational information in Hyper-relational facts. MetaRH comprises three modules: relation learning, support-specific adjustment, and query inference. By capturing meta relational information from limited support instances, MetaRH can accurately predict the missing entity in a query. As there is no existing dataset available for this new task, we construct three datasets to validate the effectiveness of MetaRH. Experimental results on these datasets demonstrate that MetaRH significantly outperforms existing representative models. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Class-Incremental Few-Shot Event Detection 30

Class-Incremental Few-Shot Event Detection

引用

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

作者： Zhao, Kailin Jin, Xiaolong Bai, Long Guo, Jiafeng Cheng, Xueqi Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China

ISBN: (纸本)9782493814104

Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few labeled instances as it is time-consuming and labor-intensive to annotate a large number of unlabeled instances. Therefore, this paper proposes a new task, called class-incremental few-shot event detection. Nevertheless, this task faces two problems, i.e., old knowledge forgetting and new class overfitting. To solve these problems, this paper further presents a novel knowledge distillation and prompt learning based method, called Prompt-KD. Specifically, to handle the forgetting problem about old knowledge, Prompt-KD develops an attention based multi-teacher knowledge distillation framework, where the ancestor teacher model pre-trained on base classes is reused in all learning sessions, and the father teacher model derives the current student model via adaptation. On the other hand, in order to cope with the few-shot learning scenario and alleviate the corresponding new class overfitting problem, Prompt-KD is also equipped with a prompt learning mechanism. Extensive experiments on two benchmark datasets, i.e., FewEvent and MAVEN, demonstrate the superior performance of Prompt-KD. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Augmentation-Aware Self-Supervision for data-Efficient GAN Training 37

Augmentation-Aware Self-Supervision for Data-Efficient GAN T...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Hou, Liang Cao, Qi Yuan, Yige Zhao, Songtao Ma, Chongyang Pan, Siyuan Wan, Pengfei Wang, Zhongyuan Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Kuaishou Technology China

ISBN: (纸本)9781713899921

Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the augmentation implicitly introduces undesired invariance to augmentation for the discriminator since it ignores the change of semantics in the label space caused by data transformation, which may limit the representation learning ability of the discriminator and ultimately affect the generative modeling performance of the generator. To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. Particularly, the prediction targets of real data and generated data are required to be distinguished since they are different during training. We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data. This formulation connects the learning objective of the generator and the arithmetic - harmonic mean divergence under certain assumptions. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures on data-limited CIFAR-10, CIFAR-100, FFHQ, LSUN-Cat, and five low-shot datasets. Experimental results demonstrate significant improvements of our method over SOTA methods in training data-efficient GANs. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Thematic Event Extraction Based on Event-Related Sentence Detection 1

Thematic Event Extraction Based on Event-Related Sentence De...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Zhang, Xing Guo, Yucan Jin, Xiaolong Liang, Haozhe Guan, Saiping School of Computer Science and Technology University of Chinese Academy of Sciences China Institute of Computing Technology Chinese Academy of Sciences Cas Key Laboratory of Network Data Science and Technology China Institute of Systems Engineering Academy of Military Science Australia

ISBN: (纸本)9798350358780

Existing works in event extraction typically extract event arguments within the sentence scope. However, besides the sentence level, events may also be naturally presented at the document level. A document-level event usually reflects, to some extent, the theme (i.e., the main content) of the document (e.g., electronic medical records and news articles), which is thus referred to as the thematic event. Thematic Event Extraction (TEE) aims to extract the arguments of thematic events. TEE faces a major challenge, i.e., the sparsity and dispersion of arguments, which means that the arguments of a thematic event are dispersed in different sentences of the document. To overcome this challenge, we propose an Event-related Sentence Detection based TEE model, called ESDTEE, which first detects the sentences related to the thematic event and then extracts the arguments only within these detected sentences using existing models. Extensive experiments with comprehensive analyses demonstrate the effectiveness of ESDTEE. © 2023 IEEE.

关键词： Medical computing

来源：评论

学校读者我要写书评

暂无评论

CausalDiff: causality-inspired disentanglement via diffusion model for adversarial defense 24

CausalDiff: causality-inspired disentanglement via diffusion...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Mingkun Zhang Keping Bi Wei Chen Quanrun Chen Jiafeng Guo Xueqi Cheng CAS Key Laboratory of AI Safety Institute of Computing Technology CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology CAS School of Statistics University of International Business and Economics

ISBN: (纸本)9798331314385

Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark). The code is available at https://***/cas-AISafetyBasicResearchGroup/CausalDiff.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation 31

MDPO: Customized Direct Preference Optimization with a Metri...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wang, Yihang Tian, Bowen Su, Yueyang Fan, Yixing Guo, Jiafeng Beijing University of Posts and Telecommunications Beijing China Guangzhou China CAS Key Lab of Network Data Science and Technology ICT CAS Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761964

With the extensive use of large language models, automatically generating QA datasets for domain-specific fine-tuning has become crucial. However, considering the multifaceted demands for readability, diversity, and comprehensiveness of QA data, current methodologies fall short in producing high-quality QA datasets. Moreover, the dependence of existing evaluation metrics on ground truth labels further exacerbates the challenges associated with the selection of QA data. In this paper, we introduce a novel method for QA data generation, denoted as MDPO. We proposes a set of unsupervised evaluation metrics for QA data, enabling multidimensional assessment based on the relationships among context,question and answer. Furthermore, leveraging these metrics, we implement a customized direct preference optimization process that guides large language models to produce high-quality and domain-specific QA pairs. Empirical results on public datasets indicate that MDPO's performance substantially surpasses that of state-of-the-art methods. © 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

On the Capacity of Citation Generation by Large Language Models

arXiv

引用

arXiv 2024年

作者： Qian, Haosheng Fan, Yixing Zhang, Ruqing Guo, Jiafeng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

Retrieval-augmented generation (RAG) appears as a promising method to alleviate the "hallucination" problem in large language models (LLMs), since it can incorporate external traceable resources for response generation. The essence of RAG in combating the hallucination issue lies in accurately attributing claims in responses to the corresponding retrieved documents. However, most of existing works focus on improving the quality of generated responses from the LLM, while largely overlooked its ability to attribute sources accurately. In this study, we conduct a systematic analysis about the capabilities of LLMs in generating citations within response generation, and further introduce a novel method to enhance their citation generation abilities. Specifically, we evaluate both the correctness and citation quality for seven widely-used LLMs on two benchmark datasets. Meanwhile, we introduce new citation evaluation metrics to eliminate the over-penalization of unnecessary and excessive citations in existing metrics. Furthermore, we propose a Generate-then-Refine method that completes relevant citations and removes irrelevant ones without altering the response text. The results on WebGLM-QA, ASQA and ELI5 datasets show that our method substantially improves the quality of citations in responses generated by LLMs. Copyright © 2024, The Authors. All rights reserved.

关键词：

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

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

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：