检索结果-内蒙古大学图书馆

Improved kernels for triangle packing in tournaments

science China(Information sciences) 2023年第5期66卷 100-113页

作者： Hanchun YUAN Qilong FENG Jianxin WANG School of Computer Science and Engineering Central South University Hunan Provincial Key Lab on Bioinformatics Central South University

Triangle packing problem has been paid lots of attention to in the literature. In this paper, we study the kernelization of the triangle packing problem in tournaments. For the parameterized arc-disjoint triangle packing problem in tournaments, we find a maximal arc-disjoint triangle packing with the number of vertices bounded by 2.5k. Based on the relation between the maximal arc-disjoint triangle packing and the vertices outside of the packing, a kernel of size 3.5k for the problem is obtained, improving the previous best one 6k. For the parameterized vertex-disjoint triangle packing problem in sparse tournaments, several new properties between the triangles in maximal vertex-disjoint triangle packing and the arcs in the feedback arc set are presented, which result in a kernel of size 7k for the problem, improving the previous best one of *** also give a 7k vertex kernel for the parameterized feedback vertex set problem in sparse *** kernelization process presented in this paper for the parameterized arc-disjoint triangle packing can be applied to solve the parameterized arc-disjoint triangle packing problem on other restricted directed graph classes.

关键词： tournaments triangle packing kernelization fixed-parameter tractable graph algorithms

来源：评论

学校读者我要写书评

暂无评论

DeepRetention:A Deep Learning Approach for Intron Retention Detection

引用

Big Data Mining and Analytics 2023年第2期6卷 115-126页

作者： Zhenpeng Wu Jiantao Zheng Jiashu Liu Cuixiang Lin Hong-Dong Li Hunan Provincial Key Lab on Bioinformatics School of Computer Science and EngineeringCentral South UniversityChangsha 410083China

As the least understood mode of alternative splicing,Intron Retention(IR)is emerging as an interesting area and has attracted more and more attention in the field of gene regulation and disease *** methods detect IR exclusively based on one or a few predefined metrics describing local or summarized characteristics of retained *** metrics are not able to describe the pattern of sequencing depth of intronic reads,which is an intuitive and informative characteristic of retained *** hypothesize that incorporating the distribution pattern of intronic reads will improve the accuracy of IR *** we present DeepRetention,a novel approach for IR detection by modeling the pattern of sequencing depth of *** to the lack of a gold standard dataset of IR,we first compare DeepRetention with two state-of-the-art methods,*** and IRFinder,on simulated RNA-seq datasets with retained *** results show that DeepRetention outperforms these two ***,DeepRetention performs well when it is applied to third-generation long-read RNA-seq data,while IRFinder and iREAD are not applicable to detecting IR from the third-generation sequencing ***,we show that IRs predicted by DeepRetention are biologically meaningful on an RNA-seq dataset from Alzheimer’s Disease(AD)*** differential IRs are found to be significantly associated with AD based on statistical evaluation of an AD-specific functional gene *** parent genes of differential IRs are enriched in AD-related *** summary,DeepRetention detects IR from a new angle of view,providing a valuable tool for IR analysis.

关键词： Alternative Splicing(AS) Intron Retention(IR) intronic reads distribution pattern RNA-seq

来源：评论

学校读者我要写书评

暂无评论

RUIE: Retrieval-based Unified Information Extraction using Large Language Model 31

RUIE: Retrieval-based Unified Information Extraction using L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Liao, Xincheng Duan, Junwen Huang, Yixi Wang, Jianxin Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Hunan Changsha China

ISBN: (纸本)9798891761964

Unified information extraction (UIE) aims to extract diverse structured information from unstructured text. While large language models (LLMs) have shown promise for UIE, they require significant computational resources and often struggle to generalize to unseen tasks. We propose RUIE (Retrieval-based Unified Information Extraction), a framework that leverages in-context learning for efficient task generalization. RUIE introduces a novel demonstration selection mechanism combining LLM preferences with a keyword-enhanced reward model, and employs a bi-encoder retriever trained through contrastive learning and knowledge distillation. As the first trainable retrieval framework for UIE, RUIE serves as a universal plugin for various LLMs. Experimental results on eight held-out datasets demonstrate RUIE's effectiveness, with average F1-score improvements of 19.22 and 3.22 compared to instruction-tuning methods and other retrievers, respectively. © 2025 Association for Computational Linguistics.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction

MARE: Multi-Aspect Rationale Extractor on Unsupervised Ratio...

引用

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

作者： Jiang, Han Duan, Junwen Qu, Zhe Wang, Jianxin Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Hunan Changsha China

ISBN: (纸本)9798891761643

Unsupervised rationale extraction aims to extract text snippets to support model predictions without explicit rationale annotation. Researchers have made many efforts to solve this task. Previous works often encode each aspect independently, which may limit their ability to capture meaningful internal correlations between aspects. While there has been significant work on mitigating spurious correlations, our approach focuses on leveraging the beneficial internal correlations to improve multi-aspect rationale extraction. In this paper, we propose a Multi-Aspect Rationale Extractor (MARE) to explain and predict multiple aspects simultaneously. Concretely, we propose a Multi-Aspect Multi-Head Attention (MAMHA) mechanism based on hard deletion to encode multiple text chunks simultaneously. Furthermore, multiple special tokens are prepended in front of the text with each corresponding to one certain aspect. Finally, multi-task training is deployed to reduce the training overhead. Experimental results on two unsupervised rationale extraction benchmarks show that MARE achieves state-of-the-art performance. Ablation studies further demonstrate the effectiveness of our method. Our codes have been available at https://***/CSU-NLP-Group/MARE. © 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

Fusion Model for Tentative Diagnosis Inference Based on Clinical Narratives

引用

Tsinghua science and Technology 2023年第4期28卷 686-695页

作者： Ying Yu Junwen Duan Min Li School of Computer Science and Engineering Central South UniversityChangsha 410083Chinaand also with the School of Computer ScienceUniversity of South ChinaHengyang 421001China Hunan Provincial Key Lab on Bioinformatics School of Computer Science and EngineeringCentral South UniversityChangsha 410083China

In general,physicians make a preliminary diagnosis based on patients’admission narratives and admission conditions,largely depending on their experiences and professional *** automatic and accurate tentative diagnosis based on clinical narratives would be of great importance to physicians,particularly in the shortage of medical *** its great value,little work has been conducted on this diagnosis ***,in this study,we propose a fusion model that integrates the semantic and symptom features contained in the clinical *** semantic features of the input text are initially captured by an attention-based Bidirectional Long Short-Term Memory(BiLSTM)*** symptom concepts,recognized from the input text,are then vectorized by using the term frequency-inverse document frequency method based on the relations between symptoms and ***,two fusion strategies are utilized to recommend the most potential candidate for the international classification of diseases *** training and evaluation are performed on a public clinical *** results show that both fusion strategies achieved a promising performance,in which the best performance obtained a top-3 accuracy of 0.7412.

关键词： tentative diagnosis clinical narrative Bidirectional Long Short-Term Memory(BiLSTM) Term FrequencyInverse Document Frequency(TF-IDF) fusion strategy

来源：评论

学校读者我要写书评

暂无评论

Local-Global Spatio-Temporal Encoding with Adaptive Brain Region Signal Segmentation for Mild Cognitive Impairment Detection

Local-Global Spatio-Temporal Encoding with Adaptive Brain Re...

引用

2024 IEEE International Conference on bioinformatics and Biomedicine, BIBM 2024

作者： Wang, Jie Wu, Luohuang Kuang, Hulin Central South University Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Hunan Changsha410000 China

ISBN: (纸本)9798350386226

Resting-state Functional Magnetic Resonance Imaging (rs-fMRI) has been widely used in Mild Cognitive Impairment (MCI) detection. However, most existing methods rely on fixed sliding windows to capture the temporal variations in brain connectivity and fail to model temporal features effectively. To address these limitations, we propose a spatio-temporal graph Transformer framework. First, we segment rs-fMRI data into distinct segments using the multivariate Gaussian distribution of brain region signals and remove redundant segments based on cumulative Jensen-Shannon divergence. Next, we extract features for each brain region and time point within segments, using these temporal features to guide spatial feature aggregation. A position encoder is designed to leverage temporal features across segments to capture both local and global spatio-temporal information. Finally, we employ a population graph framework as the classifier, with spatio-temporal features and demographic data of each subject forming the edge weights, to output the detection results. Our method achieves 92.80%, 81.89%, and 82.80% accuracy in MCI detection, early MCI detection, and late MCI detection tasks on the ADNI3 and ADNI2 datasets, respectively, outperforming existing methods. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Global Contrastive Learning with High-Quality Data in Large Vision-Language Models for Pathological Question Answering

Global Contrastive Learning with High-Quality Data in Large ...

引用

2024 IEEE International Conference on bioinformatics and Biomedicine, BIBM 2024

作者： Kuang, Hulin Liu, Suoni Zhang, Haojie Qu, Zhe Kan, Shichao Central South University Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Changsha410083 China

ISBN: (纸本)9798350386226

Pathological question answering (PQA) is vital in computational pathology, as it involves interpreting pathological images and answering questions posed by humans. This interaction offers an effective means of engaging with users and enhancing the understanding of pathology-related information. Recent methods developed using large vision-language models (LVLMs), such as QUILT-LLAVA, have made significant progress in advancing PQA. However, existing models, such as those using the QUILT-1M dataset, neglect the quality of the training set during the fine-tuning stage, leading to sub-optimal performance. We recognize that high-quality training data can significantly enhance model performance. Therefore, we design a model-based data filtering strategy to remove images with obvious impurities from the instruction fine-tuning dataset. The filtered high-quality images are then used to fine-tune the model. Additionally, most existing vision-language alignment strategies focus primarily on aligning local features through next-word prediction, leading to a relatively homogeneous granularity in inter-modal alignment. To address this issue, we propose a global-wise alignment module, which introduces global-level contrastive learning during the pretraining stage to establish multi-granularity alignment between pathological images and language descriptions. Based on the above two processes, we design our method, named Global Contrastive Learning with High-Quality Data (GCL-HQD) for pathological question answering in LVLMs. Extensive experiments on two types of experimental settings demonstrate the effectiveness of the GCL-HQD method. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

KEXNet:A Knowledge-Enhanced Model for Improved Chest X-Ray Lesion Detection

引用

Big Data Mining and Analytics 2024年第4期7卷 1187-1198页

作者： Quan Yan Junwen Duan Jianxin Wang School of Computer Science and Engineering and Hunan Provincial Key Lab on Bioinformatics Central South UniversityChangsha 410083China

Automated diagnosis of chest X-rays is pivotal in radiology,aiming to alleviate the workload of *** methods primarily rely on visual features or label dependence,which is a limitation in detecting nuanced or rare *** address this,we present KEXNet,a pioneering knowledge-enhanced X-ray lesion detection *** employs a unique strategy akin to expert radiologists,integrating a knowledge graph based on expert annotations with an interpretable graph learning *** novel method combines object detection with a graph neural network,facilitating precise local lesion *** global lesion detection,KEXNet synergizes knowledge-enhanced local features with global image features,enhancing diagnostic *** evaluations on three benchmark datasets demonstrate that KEXNet outshines existing models,particularly in identifying small or infrequent ***,on the Chest ImaGenome dataset,KEXNet’s AUC for local lesion detection surpasses 8.9%compared to the state-of-the-art method AnaXNet,showcasing its potential in revolutionizing automated chest X-ray diagnostics.

关键词： multi-label chest X-ray classification object detection knowledge graph learning

来源：评论

学校读者我要写书评

暂无评论

medIKAL: Integrating Knowledge Graphs as Assistants of LLMs for Enhanced Clinical Diagnosis on EMRs 31

medIKAL: Integrating Knowledge Graphs as Assistants of LLMs ...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Jia, Mingyi Duan, Junwen Song, Yan Wang, Jianxin Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University China University of Science and Technology of China China

ISBN: (纸本)9798891761964

Electronic Medical Records (EMRs), while integral to modern healthcare, present challenges for clinical reasoning and diagnosis due to their complexity and information redundancy. To address this, we proposed medIKAL (Integrating Knowledge Graphs as Assistants of LLMs), a framework that combines Large Language Models (LLMs) with knowledge graphs (KGs) to enhance diagnostic capabilities. medIKAL assigns weighted importance to entities in medical records based on their type, enabling precise localization of candidate diseases within KGs. It innovatively employs a residual network-like approach, allowing initial diagnosis by LLMs to be merged into KG search results. Through a path-based reranking algorithm and a fill-in-the-blank style prompt template, it further refined the diagnostic process. We validated medIKAL's effectiveness through extensive experiments on a newly introduced open-sourced Chinese EMR dataset, demonstrating its potential to improve clinical diagnosis in real-world settings. The code and dataset are publicly available at https://***/CSU-NLP-Group/mediKAL. © 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

FBC: Fusing Bi-Encoder and Cross-Encoder for Long-Form Text Matching 26

FBC: Fusing Bi-Encoder and Cross-Encoder for Long-Form Text ...

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Liao, Jianbo Jia, Mingyi Duan, Junwen Wang, Jianxin Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University China

ISBN: (纸本)9781643684369

Semantic text matching has a wide range of applications in natural language processing. Recently proposed models that have achieved excellent results on short text matching tasks are not well suited to long-form text matching problems due to input length limitations and increased noise. On the other hand, long-form texts contain a large amount of information at different granularities after encoding, which cannot be fully interacted and utilized by existing methods. To address above issues, we propose a novel long-form text-matching framework which fuses Bi-Encoder and Cross-Encoder (FBC). Specially, it first employs an entity-driven key sentence extraction method to obtain the crucial content of the text and filter out noise. Subsequently, it integrates Bi-Encoder and Cross-Encoder to better capture semantic features and matching signals. Extensive experiments on several publicly available datasets demonstrate the effectiveness of our approach, compared with strong baselines. Furthermore, our model exhibits greater stability and accuracy in determining the matching relationship between documents describing the same event, which outperforms previously established approaches. The code is released at https://***/CSU-NLP-Group/FBC. © 2023 The Authors.

关键词： Semantics

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：