检索结果-内蒙古大学图书馆

SEE-Few: Seed, Expand and Entail for Few-shot Named Entity Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Zeng Zhang, Linhai Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. Current few-shot NER methods focus on leveraging existing datasets in the rich-resource domains which might fail in a training-from-scratch setting where no source-domain data is used. To tackle training-from-scratch setting, it is crucial to make full use of the annotation information (the boundaries and entity types). Therefore, in this paper, we propose a novel multitask (Seed, Expand and Entail) learning framework, SEE-Few, for Few-shot NER without using source domain data. The seeding and expanding modules are responsible for providing as accurate candidate spans as possible for the entailing module. The entailing module reformulates span classification as a textual entailment task, leveraging both the contextual clues and entity type information. All the three modules share the same text encoder and are jointly learned. Experimental results on four benchmark datasets under the training-from-scratch setting show that the proposed method outperformed state-of-the-art few-shot NER methods with a large margin. Copyright © 2022, The Authors. All rights reserved.

关键词： Classification (of information)

Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Si, Jiasheng Zhu, Yingjie Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

The opaqueness of the multi-hop fact verification model imposes imperative requirements for explainability. One feasible way is to extract rationales, a subset of inputs, where the performance of prediction drops dramatically when being removed. Though being explainable, most rationale extraction methods for multi-hop fact verification explore the semantic information within each piece of evidence individually, while ignoring the topological information interaction among different pieces of evidence. Intuitively, a faithful rationale bears complementary information being able to extract other rationales through the multi-hop reasoning process. To tackle such disadvantages, we cast explainable multi-hop fact verification as subgraph extraction, which can be solved based on graph convolutional network (GCN) with salience-aware graph learning. In specific, GCN is utilized to incorporate the topological interaction information among multiple pieces of evidence for learning evidence representation. Meanwhile, to alleviate the influence of noisy evidence, the salience-aware graph perturbation is induced into the message passing of GCN. Moreover, the multi-task model with three diagnostic properties of rationale is elaborately designed to improve the quality of an explanation without any explicit annotations. Experimental results on the FEVEROUS benchmark show significant gains over previous state-of-the-art methods for both rationale extraction and fact verification. Copyright © 2022, The Authors. All rights reserved.

关键词： Message passing

Timo: In-memory temporal query processing for big temporal data

学校读者我要写书评

暂无评论

Timo: In-memory temporal query processing for big temporal d...

作者： Zheng, Xiao Liu, Houkai Wang, Xiujun Wu, Xuangou Yu, Feng School of Computer Science and Technology Anhui University of Technology Maanshan China Institute for Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Anhui Engineering Laboratory for Intelligent Applications and Security of Industrial Internet Anhui University of Technology Anhui Maanshan China School of Computer Science and Engineering & School of Software Guangxi Normal University Guilin China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China

Today's internet applications generate massive temporal data anywhere and anytime. Although some disk-based temporal systems are currently available, they suffer from poor I/O performance, especially when applied in intelligent applications deployed in the cloud and edge environments. Therefore, how to process temporal operations with low latency and high throughput becomes a crucial problem for efficient data processing. This paper proposes Timo, a distributed in-memory temporal query and analytic model for big temporal data. Firstly, a space-efficient temporal index is proposed to support more efficiently query performance with less memory space than the state-of-art methods. Secondly, based on the temporal locality feature of temporal queries, Timo proposes a partitioner mechanism, which utilizes forward scan algorithm, to improve query throughput. Thirdly, some optimal strategies are proposed to improve the execution process of temporal query and analysis, which reduce intermediate result data size and improve the throughput much further. Lastly, we implement the Timo system on the Apache Spark platform, which extends Spark dataset API with temporal query and analysis API functions for users. Extensive experimental results show that the Timo system outperforms other Spark-based temporal systems in terms of both query latency and throughput. © 2021 John Wiley & Sons, Ltd.

关键词： Data handling

Continuous contrastive learning for long-tailed semi-supervised recognition 24

学校读者我要写书评

暂无评论

Continuous contrastive learning for long-tailed semi-supervi...

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

作者： Zi-Hao Zhou Siyuan Fang Zi-Jing Zhou Tong Wei Yuanyu Wan Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China Xiaomi Inc. China School of Software Technology Zhejiang University Ningbo China

ISBN: (纸本)9798331314385

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. Our source code is available at https://***/zhouzihao11/CCL.

关键词：

Deep Convolutional Dictionary Learning network for Sparse View Ct Reconstruction with a Group Sparse Prior

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Kang, Yanqin Liu, Jin Wu, Fan Wang, Kun Qiang, Jun Hu, Dianlin Zhang, Yikun College of Computer and Information Anhui Polytechnic University Wuhu China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China School of Computer Science and Engineering Southeast University Nanjing China

Purpose: Many deep learning-based methods have been applied in sparse view computed tomography (CT) imaging. However, most methods are built intuitively using state-of-the-art black-box convolutional neural networks (CNNs) and lack interpretability. Moreover, CNNs tend to focus on local receptive fields, neglecting nonlocal self-similarity prior information. How to obtain diagnostically useful images from sparsely sampled projections is a challenging, ill-posed ***: To address this issue, we propose a novel interpretable model based on a convolutional dictionary learning network and nonlocal group sparse prior, called DCDL-GS, for sparse view CT image reconstruction. We apply a statistical iterative reconstruction algorithm for a fixed number of iterations with a neural network to improve the image reconstruction quality. Inspired by a group sparsity prior, we adopt a novel group thresholding operation to improve the feature representation and constraint ability and obtain a theoretical interpretation. Additionally, filtered backprojection (FBP) reconstruction, fast sliding window nonlocal self-similarity operations, and a lightweight convolutional dictionary learning network are integrated into our DCDL-GS model, improving model ***: The visual results based on the LDCT-P and UIH datasets show the efficiency of our proposed DCDL-GS model in edge preservation and feature recovery. The quantitative results show improvement over state-of-the-art methods, with improvements of 0.6-0.8 dB for the peak signal-to-noise ratio (PSNR), 0.005-0.01 for the structural similarity index measure (SSIM), and 1-1.3 for the regulated Fréchet inception distance (rFID) based on the test dataset. The quantitative results also show the effectiveness of our proposed deep convolution iterative reconstruction module and nonlocal group sparse ***: We developed a unified optimized mathematical model incorporating projection data and image prior knowled

关键词： Image reconstruction

Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yanyue Li, Pengfei Lai, Yilong Zhou, Deyu He, Yulan School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King’s College London United Kingdom The Alan Turing Institute United Kingdom

As more than 70% of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are reluctant to generate negative summaries given the input of negative texts. To address such sentiment bias, a direct approach without the over-reliance on a specific framework is to generate additional data based on large language models to balance the emotional distribution of the dataset. However, data augmentation based on large language models faces two disadvantages: 1) the potential issues or toxicity in the augmented data;2) the expensive costs. Therefore, in this paper, we propose a novel data augmentation framework based on both large and small language models for debiasing opinion summarization. In specific, a small size of synthesized negative reviews is obtained by rewriting the positive text via a large language model. Then, a disentangle reconstruction model is trained based on the generated data. After training, a large amount of synthetic data can be obtained by decoding the new representation obtained from the combination of different sample representations and filtering based on confusion degree and sentiment classification. Experiments have proved that our framework can effectively alleviate emotional bias same as using only large models, but more economically. Copyright © 2024, The Authors. All rights reserved.

关键词： Data assimilation

Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Congzhi Zhang, Linhai Wu, Jialong He, Yulan Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King’s College London United Kingdom The Alan Turing Institute United Kingdom

Despite the notable advancements of existing prompting methods, such as In-Context Learning and Chain-of-Thought for Large Language Models (LLMs), they still face challenges related to various biases. Traditional debiasing methods primarily focus on the model training stage, including approaches based on data augmentation and reweighting, yet they struggle with the complex biases inherent in LLMs. To address such limitations, the causal relationship behind the prompting methods is uncovered using a structural causal model, and a novel causal prompting method based on front-door adjustment is proposed to effectively mitigate LLMs biases. In specific, causal intervention is achieved by designing the prompts without accessing the parameters and logits of LLMs. The chain-of-thought generated by LLM is employed as the mediator variable and the causal effect between input prompts and output answers is calculated through front-door adjustment to mitigate model biases. Moreover, to accurately represent the chain-of-thoughts and estimate the causal effects, contrastive learning is used to fine-tune the encoder of chain-of-thought by aligning its space with that of the LLM. Experimental results show that the proposed causal prompting approach achieves excellent performance across seven natural language processing datasets on both open-source and closed-source LLMs. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

Topology Uncertainty Modeling For Imbalanced Node Classification on Graphs

学校读者我要写书评

暂无评论

Topology Uncertainty Modeling For Imbalanced Node Classifica...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jiayi Gao Jiaxing Li Ke Zhang Youyong Kong Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing China Ministry of Education Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China

Most existing graph neural networks work under a class-balanced assumption, while ignoring class-imbalanced scenarios that widely exist in real-world graphs. Although there are many methods in other fields that can alleviate this issue, they do not consider the special topology of the non-Euclidean graph. Hence, we propose Graph Topology Uncertainty (GraphTU), a novel probabilistic class-imbalanced solution specifically for graphs. Firstly, an invisible "uncertain gap" between under-represented minorities in training set and authentic minorities in unseen set is modeled by estimating statistical variances in topology. We extend the training distribution for minorities by sampling in this gap through a non-parametric way. Moreover, a gradient-guided mask is introduced to prevent biased statistics. Extensive experiments demonstrate the superior performance of GraphTU.

关键词： Training Uncertainty network topology Signal processing Probabilistic logic Graph neural networks Acoustics

Topgformer: Topological-Based Graph Transformer for Mapping Brain Structural Connectivity to Functional Connectivity

学校读者我要写书评

暂无评论

Topgformer: Topological-Based Graph Transformer for Mapping ...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Dalu Guo Ke Zhang Jiaxing Li Youyong Kong Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China

Exploring the mapping between structural connectivity (SC) and functional connectivity (FC) is of essential importance to understanding the working mechanism of the human brain. Traditional methods are difficult to represent the complex relationship of high-order interaction between SC and FC. Recent learning-based methods can not well capture the important long-range interactions and edge information of brain connectivity. To address the issue, we propose a novel Topological-based Graph Transformer (TopGFormer) to generate functional connectivity from the structure connectivity with sufficient consideration of topological properties of brain connectivity. We propose a Topological Multi-Head Attention block that simultaneously uses centrality encoding and adjacency matrix to capture node and edge importance respectively. The centrality encoding reflects the importance of brain regions while the adjacency matrix captures the linking relationship of different regions. Experiments on HCP resting and emotion task datasets demonstrate the performance of the proposed method.

关键词： Learning systems Brain Correlation Signal processing Transformers Encoding Acoustics