检索结果-内蒙古大学图书馆

Siamese transformer with hierarchical concept embedding for fine-grained image recognition

Science China(Information Sciences) 2023年第3期66卷 188-203页

作者： Yilin LYU Liping JING Jiaqi WANG Mingzhe GUO Xinyue WANG Jian YU School of Computer and Information Technology Beijing Jiaotong University Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Alibaba Group

Distinguishing the subtle differences among fine-grained images from subordinate concepts of a concept hierarchy is a challenging task. In this paper, we propose a Siamese transformer with hierarchical concept embedding(STr HCE), which contains two transformer subnetworks sharing all configurations,and each subnetwork is equipped with the hierarchical semantic information at different concept levels for fine-grained image embeddings. In particular, one subnetwork is for coarse-scale patches to learn the discriminative regions with the aid of the innate multi-head self-attention mechanism of the transformer. The other subnetwork is for finer-scale patches, which are adaptively sampled from the discriminative regions, to capture subtle yet discriminative visual cues and eliminate redundant information. STr HCE connects the two subnetworks through a score margin adjustor to enforce the most discriminative regions generating more confident predictions. Extensive experiments conducted on four commonly-used benchmark datasets, including CUB-200-2011, FGVC-Aircraft, Stanford Dogs, and NABirds, empirically demonstrate the superiority of the proposed STr HCE over state-of-the-art baselines.

关键词： fine-grained image recognition transformer hierarchical concept embedding adaptive sampling Siamese network

来源：评论

学校读者我要写书评

暂无评论

Noisy Multi-Label Text Classification via Instance-Label Pair Correction

Noisy Multi-Label Text Classification via Instance-Label Pai...

引用

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Xu, Pengyu Song, Mingyang Liu, Linkaida Liu, Bing Sun, Hongjian Jing, Liping Yu, Jian Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China

ISBN: (纸本)9798891761193

In noisy label learning, instance selection based on small-loss criteria has been proven to be highly effective. However, in the case of noisy multi-label text classification (NMLTC), the presence of noise is not limited to the instance-level but extends to the (instance-label) pair-level. This gives rise to two main challenges. (1) The loss information at the pair-level fails to capture the variations between instances. (2) There are two types of noise at the pair-level: false positives and false negatives. Identifying false negatives from a large pool of negative pairs presents an exceedingly difficult task. To tackle these issues, we propose a novel approach called instance-label pair correction (iLaCo), which aims to address the problem of noisy pair selection and correction in NMLTC tasks. Specifically, we first introduce a holistic selection metric that identifies noisy pairs by simultaneously considering global loss information and instance-specific ranking information. Secondly, we employ a filter guided by label correlation to focus exclusively on negative pairs with label relevance. This filter significantly reduces the difficulty of identifying false negatives. Experimental analysis indicates that our iLaCo framework effectively corrects noisy pairs in NMLTC datasets, leading to a significant improvement in model performance. © 2024 Association for Computational Linguistics.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Dual-Space Knowledge Distillation for Large Language Models

Dual-Space Knowledge Distillation for Large Language Models

引用

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

作者： Zhang, Songming Zhang, Xue Sun, Zengkui Chen, Yufeng Xu, Jinan Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China

ISBN: (纸本)9798891761643

Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller *** this process, white-box KD methods usually minimize the distance between the output distributions of the two models so that more knowledge can be ***, in the current white-box KD framework, the output distributions are from the respective output spaces of the two models, using their own prediction *** argue that the space discrepancy will lead to low similarity between the teacher model and the student model on both representation and distribution ***, this discrepancy also hinders the KD process between models with different vocabularies, which is common for current *** address these issues, we propose a dual-space knowledge distillation (DSKD) framework that unifies the output spaces of the two models for *** the basis of DSKD, we further develop a cross-model attention mechanism, which can automatically align the representations of the two models with different ***, our framework is not only compatible with various distance functions for KD (e.g., KL divergence) like the current framework, but also supports KD between any two LLMs regardless of their *** on task-agnostic instruction-following benchmarks show that DSKD significantly outperforms the current white-box KD framework with various distance functions, and also surpasses existing KD methods for LLMs with different vocabularies. © 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

CollabKG: A Learnable Human-Machine-Cooperative Information Extraction Toolkit for (Event) Knowledge Graph Construction 30

CollabKG: A Learnable Human-Machine-Cooperative Information ...

引用

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

作者： Wei, Xiang Chen, Yufeng Cheng, Ning Cui, Xingyu Xu, Jinan Han, Wenjuan Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China

ISBN: (纸本)9782493814104

In order to construct or extend entity-centric and event-centric knowledge graphs (KG and EKG), the information extraction (IE) annotation toolkit is essential. However, existing IE toolkits have several non-trivial problems, such as not supporting multi-tasks, and not supporting automatic updates. In this work, we present CollabKG, a learnable human-machine-cooperative IE toolkit for KG and EKG construction. Specifically, for the multi-task issue, CollabKG unifies different IE subtasks, including named entity recognition (NER), entity-relation triple extraction (RE), and event extraction (EE), and supports both KG and EKG. Then, combining advanced prompting-based IE technology, the human-machine-cooperation mechanism with Large Language Models (LLMs) as the assistant machine is presented which can provide a lower cost as well as a higher performance. Lastly, owing to the two-way interaction between the human and machine, CollabKG with learning ability allows self-renewal. Besides, CollabKG has several appealing features (e.g., customization, training-free, and label propagation) that make the system powerful and high-productivity. We holistically compare our toolkit with other existing tools on these features. Human evaluation quantitatively illustrates that CollabKG significantly improves annotation quality, efficiency, and stability simultaneously. © 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

Dynamic Simulation Benchmark for Motion Coordination Tasks

Dynamic Simulation Benchmark for Motion Coordination Tasks

引用

2024 IEEE International Conference on Unmanned Systems, ICUS 2024

作者： Han, Sheng Ji, Yuning Lin, Youfang Lv, Kai School of Computer and Information Technology Beijing Jiaotong University Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing China

ISBN: (纸本)9798350384185

Existing motion coordination simulation environments can only support a limited number of preset scenarios and lack the capability to simulate complex dynamic environments, which hinders the fulfillment of practical needs and restricts the generalization ability and training effectiveness of algorithms. This paper proposes an innovative simulation environment that supports the simulation of complex dynamic environments and offers flexible configuration. It can dynamically adjust to meet different testing requirements, thereby enhancing the generalization ability and training speed of algorithms while maintaining sufficient environmental complexity to ensure training effectiveness. Experimental results show that the new simulation environment performs excellently in complex dynamic scenarios, significantly improving the generalization ability and training efficiency of algorithms. This provides a more reliable and efficient solution for the training and validation of algorithms for motion coordination tasks. © 2024 IEEE.

关键词： dynamic environment simulation motion coordination for multiple moving objects motion coordination simulation environment

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multi-Label Text Classification under Label-Dependent Noise: A Label-Specific Denoising Framework

Enhancing Multi-Label Text Classification under Label-Depend...

引用

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

作者： Xu, Pengyu Jing, Liping Yu, Jian Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China

ISBN: (纸本)9798891761681

Recent advancements in noisy multi-label text classification have primarily relied on the class-conditional noise (CCN) assumption, which treats each label independently undergoing label flipping to generate noisy labels. However, in real-world scenarios, noisy labels often exhibit dependencies with true labels. In this study, we validate through hypothesis testing that real-world datasets are unlikely to adhere to the CCN assumption, indicating that label noise is dependent on the current labels. To address this, we introduce a label-specific denoising framework designed to counteract label-dependent noise. The framework initially presents a holistic selection metric that evaluates noisy labels by concurrently considering loss information, ranking information, and feature centroid. Subsequently, it identifies and corrects noisy labels individually for each label category in a fine-grained manner. Extensive experiments on benchmark datasets demonstrate the effectiveness of our method under both synthetic and real-world noise conditions, significantly improving performance over existing state-of-the-art models. © 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

SKICSE: Sentence Knowable Information Prompted by LLMs Improves Contrastive Sentence Embeddings

SKICSE: Sentence Knowable Information Prompted by LLMs Impro...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Ou, Fangwei Xu, Jinan Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China

Contrastive learning, which utilizes positive pairs and in-batch negatives to optimize the loss objective, has been proven to be an effective method for learning sentence embeddings. However, we argue that the previous methods of constructing positive pairs only through dropout perturbation or entailment relation are limited. Since there is more sentence knowable information (SKI) to be mined, such as sentence external knowledge, semantic analysis, and grammatical description. In this work, we first hand-craft a simple and effective prompt template that is able to obtain the knowable information of input sentences from LLMs (e.g., LLaMA). Then we combine the original sentence and its knowable information to form a positive pair for contrastive learning. We evaluate our method on standard semantic textual similarity (STS) tasks. Experimental results show that our unsupervised and supervised models using BERTbase achieve an average of 78.65% and 82.45% Spearman’s correlation respectively, a 2.40% and 0.88% improvement compared to SimCSE. Our model outperforms the previous state-of-the-art model PromptBERT in both unsupervised and supervised settings and specifically yields a new state-of-the-art performance in supervised setting. © 2024 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

DiffLight: A Partial Rewards Conditioned Diffusion Model for traffic Signal Control with Missing data 38

DiffLight: A Partial Rewards Conditioned Diffusion Model for...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Hanyang Jiang, Yang Guo, Shengnan Mao, Xiaowei Lin, Youfang Wan, Huaiyu School of Computer Science and Technology Beijing Jiaotong University China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing China

The application of reinforcement learning in traffic signal control (TSC) has been extensively researched and yielded notable achievements. However, most existing works for TSC assume that traffic data from all surrounding intersections is fully and continuously available through sensors. In real-world applications, this assumption often fails due to sensor malfunctions or data loss, making TSC with missing data a critical challenge. To meet the needs of practical applications, we introduce DiffLight, a novel conditional diffusion model for TSC under data-missing scenarios in the offline setting. Specifically, we integrate two essential sub-tasks, i.e., traffic data imputation and decision-making, by leveraging a Partial Rewards Conditioned Diffusion (PRCD) model to prevent missing rewards from interfering with the learning process. Meanwhile, to effectively capture the spatial-temporal dependencies among intersections, we design a Spatial-Temporal transFormer (STFormer) architecture. In addition, we propose a Diffusion Communication Mechanism (DCM) to promote better communication and control performance under data-missing scenarios. Extensive experiments on five datasets with various data-missing scenarios demonstrate that DiffLight is an effective controller to address TSC with missing data. The code of DiffLight is released at https://***/lokol5579/DiffLight-release. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

KG-FPQ: Evaluating Factuality Hallucination in LLMs with Knowledge Graph-based False Premise Questions 31

KG-FPQ: Evaluating Factuality Hallucination in LLMs with Kno...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhu, Yanxu Xiao, Jinlin Wang, Yuhang Sang, Jitao Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China Peng Cheng Lab China

ISBN: (纸本)9798891761964

Recent studies have demonstrated that large language models (LLMs) are susceptible to being misled by false premise questions (FPQs), leading to errors in factual knowledge, known as factuality hallucination. Existing benchmarks that assess this vulnerability primarily rely on manual construction, resulting in limited size and lack of expandability. In this work, we introduce an automated, scalable pipeline to create FPQs based on knowledge graphs (KGs). The first step is to modify true triplets extracted from KGs to create false premises. Subsequently, utilizing the state-of-the-art capabilities of GPTs, we generate semantically rich FPQs. Based on the proposed method, we present a comprehensive benchmark, the Knowledge Graph-based False Premise Questions (KG-FPQ), which contains approximately 178k FPQs across three knowledge domains, at six levels of confusability, and in two task formats. Using KG-FPQ, we conduct extensive evaluations on several representative LLMs and provide valuable insights. The KG-FPQ dataset and code are available at https://***/yanxuzhu/KG-FPQ. © 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

Detection, Diagnosis, and Explanation: A Benchmark for Chinese Medical Hallucination Evaluation 30

Detection, Diagnosis, and Explanation: A Benchmark for Chine...

引用

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

作者： Dou, Chengfeng Zhang, Ying Chen, Yanyuan Jin, Zhi Jiao, Wenpin Zhao, Haiyan Zhao, Yongqiang Tao, Zhenwei Huang, Yun MOE China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China

ISBN: (纸本)9782493814104

Large Language Models (LLMs) have made significant progress recently. However, their practical use in healthcare is hindered by their tendency to generate hallucinations. One specific type, called snowballing hallucination, occurs when LLMs encounter misleading information, and poses a security threat to LLMs. To understand how well LLMs can resist these hallucination, we create the Chinese Medical Hallucination Evaluation benchmark (CMHE). This benchmark can be used to evaluate LLMs' ability to detect medical hallucinations, make accurate diagnoses in noisy conditions, and provide plausible explanations. The creation of this benchmark involves a combination of manual and model-based approaches. In addition, we use ICD-10 as well as MeSH, two specialized glossaries, to aid in the evaluation. Our experiments show that the LLM struggles to identify fake medical terms and makes poor diagnoses in distracting environments. However, improving the model's understanding of medical concepts can help it resist interference to some extent. Our dataset is available at https://***/drive/folders/1DrdovKwZIh6AX_JjL8BVpUmI9djiIwn_?usp=drive_link. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Diagnosis

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：