检索结果-内蒙古大学图书馆

2024 international conference on knowledge engineering and Communication Systems, ICKECS 2024

作者： Thakur, Gopal Kumar Thakur, Abhishek Khan, Naseebia Anush, Hannah Harrisburg University of Science & Technology Department of Data Science HarrisburgPA United States Harrisburg University Department of Data Science HarrisburgPA United States Campbellsville University Department of Management and Technology CampbellsvilleKY United States

ISBN: (纸本)9798350359688

In recent years, the intersection of natural language processing (NLP) and healthcare has emerged as a frontier for innovation, offering new pathways to enhance medical data analysis and healthcare automation. This paper explores the pivotal role of NLP technologies in transforming healthcare operations, patient care, and medical research. With the exponential growth of unstructured medical data, including clinical notes, electronic health records (EHRs), and research publications, the application of NLP techniques presents a significant opportunity for extracting meaningful information, thus facilitating improved decision-making processes in medical practice. We delve into the mechanisms through which NLP algorithms interpret, analyze, and generate human language, enabling the automation of tasks such as symptom checking, patient triage, and personalized treatment plans. Furthermore, the paper presents a comprehensive review of the current literature, highlighting the advancements, challenges, and future directions in the field. Our proposed work introduces a novel NLP-based framework designed to optimize the analysis of medical data, featuring the implementation of state-of-the-art algorithms and mathematical models. Through empirical research, we demonstrate the efficacy of our framework in enhancing diagnostic accuracy, predicting patient outcomes, and streamlining healthcare services. The results section discusses the findings from the implementation, supported by graphs and tables, which underscore the transformative potential of NLP in healthcare. Finally, the conclusion summarizes the key insights and envisages the future landscape of NLP-driven healthcare innovations. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

A HYDRO-POWER SAFETY MANAGEMENT AUXILIARY DECISION-MAKING PLATFORM DESIGN USING natural language processing TECHNOLOGIES 2

A HYDRO-POWER SAFETY MANAGEMENT AUXILIARY DECISION-MAKING PL...

引用

2nd international conference on Power, Communication, Computing and Networking Technologies, PCCNT 2024

作者： Duan, Peng Zhang, Xiaoyu Liu, Xianke Yang, Peng Jiao, Jiangming China Yangtze Power Corporation Three Gorges Power Plant Yichang443000 China

ISBN: (纸本)9781837242672

The safety management construction of the hydro-power units is necessary to prevent the quality failures. However, the traditional hydro-power units lack a unified safety management decision-making platform, making knowledge retrieval and recommendation difficult. To improve the safety management level of the hydro-power units, this work designs an auxiliary decision-making platform using natural language processing technologies. The auxiliary decision-making platform is composed of three parts, deep semantic similarity model, bidirectional long short-term memory network model and neural collaborative filtering algorithm. A case study is conducted to validate the auxiliary decision-making platform, which can provide the user the relevant knowledge guidance to the problem, including dangerous point analysis, defect causes, handling methods and operation preparation, improving the safety management level of the hydro-power units. © The Institution of engineering & Technology 2024.

关键词： Hydro energy

来源：评论

学校读者我要写书评

暂无评论

"Reasoning before Responding": Towards Legal Long-form Question Answering with Interpretability 24

"Reasoning before Responding": Towards Legal Long-form Quest...

引用

33rd ACM international conference on Information and knowledge Management (CIKM)

作者： Ujwal, Utkarsh Surampudi, Sai Sri Harsha Mitra, Sayantan Saha, Tulika Univ Liverpool Liverpool Merseyside England JPMorgan Chase & Co Bengaluru India

ISBN: (纸本)9798400704369

Long-Form Question Answering (LFQA) represents a growing interest in Legal natural language processing (Legal-NLP) as many individuals encounter legal disputes at some point in their lives, but lack of knowledge about how to negotiate these complex situations might put them at risk. The endeavor to generate detailed answers to contextually rich legal questions has faced challenges, primarily due to the limited availability of specialized datasets involving intensive manual effort or incapability of existing LFQA models to produce informative responses. Addressing this, our research introduces a semi-synthetic dataset, Legal-LFQA (L2FQA) created by exploiting a large language model (LLM) and utilizing contexts derived from existing legal datasets. Additionally, we hypothesize that integrating legal reasoning into the answer generation process of the LLMs will help bolster both the quality and interpretability of the produced responses. We systematically analyze the quality of L2FQA using human evaluation and natural language inference based metrics. Next, we benchmark L2FQA on a wide range of general-purpose and domain-specific LLMs using fine-tuning and in-context learning (with zero, one and few shot) strategies. The efficacy of these techniques is gauged through several automated and human evaluations. Results indicate that incorporating legal reasoning into the answer generation process provides an avenue for improving the quality of responses in the context of Legal-LFQA task. By addressing the challenges faced in LFQA and emphasizing the potential of interpretability, this research contributes to the foundational work in enhancing question-answering systems within the legal domain.

关键词： Long-Form Question Answering Legal Domain Large language Models Interpretability

来源：评论

学校读者我要写书评

暂无评论

A Concise Review of Long Context in Large language Models 24

A Concise Review of Long Context in Large Language Models

引用

international conference on Algorithms, Software engineering, and Network Security (ASENS)

作者： Huang, Haitao Liang, Zijing Fang, Zirui Wang, Zhiyuan Chen, Mingxiu Hong, Yifan Liu, Ke Shang, Penghui Zhiyuan Res Inst Hangzhou 310000 Zhejiang Peoples R China

ISBN: (纸本)9798400709784

Sincerely in part to the rise of high-performance computer systems and transformer models, natural language processing has advanced. Also, a multitude of applications built on large language models continually improve people's cognitive abilities. Large language models continue to face difficulties when dealing with long context input. Many studies have suggested various specific strategies to address the challenge of extended context, however as of yet, no thorough summary of these studies exists. In this paper, we discuss the issues raised and the developments that have occurred in the long context application of large language models, and we attempt to suggest future directions for research and development.

关键词： Component Large language model Long context Self-attention Retrieval augment

来源：评论

学校读者我要写书评

暂无评论

Enhance Large language Models for Multilingual Sentence Embedding with knowledge Graph

Enhance Large Language Models for Multilingual Sentence Embe...

引用

international Joint conference on Neural Networks (IJCNN)

作者： Wang, ZhenYu Wu, Yifei Donghua Univ Sch Comp Sci & Technol Shanghai Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Sentence representation is a major challenge in natural language processing, especially in multilingual environments. Current approaches to sentence representation using Large language Models (LLMs) often require large amounts of data for fine-tuning, and research has focused on English content. In addition, comparative datasets translated directly from English can contain many semantic and syntactic errors. To address these issues, we propose a new approach to enhance multilingual sentence embeddings using LLMs and knowledge graphs. We first present a dedicated designed prompt that exploits in-context learning of LLMs for sentence embedding without fine-tuning. We further introduce an innovative method that utilizes knowledge graphs, such as Wikidata, for generating diverse multilingual training data for contrastive finetuning. This approach significantly reduces the reliance on translated sentences and mitigates issues related to translation accuracy. Furthermore, we develop a unique multilingual contrastive learning loss function, which, when combined with QLora's efficient fine-tuning technique, enables LLMs to achieve state-of-the-art performance in Sentence Text Similarity (STS) tasks, even with limited computational resources.

关键词： sentence embedding contrastive learning large language model data argumentation

来源：评论

学校读者我要写书评

暂无评论

Enhanced BERT with Graph and Topic Information for Short Text Classification 35

Enhanced BERT with Graph and Topic Information for Short Tex...

引用

35th international conference on Software engineering and knowledge engineering, SEKE 2023

作者： Zhang, Tong Tang, Ailing Yan, Rong College of Computer Science Inner Mongolia University Inner Mongolia Key Laboratory of Mongolian Information Processing Technology National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot010021 China

Short text classification is an important natural language processing task due to the prevalence of short text on the internet and social media platforms. In this paper, we propose a novel graph-based short text classification method named GBBM (Graph-BERT-BTM Model) that leverages the powerful representation ability of graph data to capture the structural features of short text. In this work, we incorporate topic information to enrich and expand the feature space for the short text and compare our proposed method on five publicly available short text datasets with five existing models. Experimental results indicate the superiority of our proposed method. © 2023 knowledge Systems Institute Graduate School. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Integrated Geologic Terms and Dual Model for Chinese Geological Word Segmentation 17th

Integrated Geologic Terms and Dual Model for Chinese Geologi...

引用

17th international conference on knowledge Science, engineering and Management (KSEM)

作者： Cheng, Shupeng Wu, Kunkun Liu, Xiao Tang, Xianxing Hu, Maosheng China Univ Geosci Sch Comp Sci Wuhan 430074 Peoples R China China Univ Geosci Natl Engn Res Ctr Geog Informat Syst Wuhan 430074 Peoples R China

ISBN: (纸本)9789819755004;9789819755011

Mining knowledge from the rapid growth geological documents is essential for the development of geoscience. languages such as Chinese, which consist of continuous characters, are difficult for computer processing and understanding, and word segmentation is a prerequisite in this situation. The quality of word segmentation has a crucial impact on the correct completion of downstream tasks, such as named entity recognition, relationship extraction and dependency analysis. Due to the specialization and complexity of the documents in the geological field, tools and models built in general domain usually have a poor performance in solving this problem. In this paper, we propose a new model named DualBERT which combines general model with domain model, and provides the ability to adapt to the new scenarios while maintaining the adaptability to the original scene. We introduce a words segmentation correction method based on the similarity with geologic terms, in order to enhance the ability to identify the boundaries of highly domain-specific geologic terms.

关键词： Chinese geological word segmentation Domain-adaptive natural language processing Dual model similarity with geologic terms

来源：评论

学校读者我要写书评

暂无评论

Towards Safe, Secure, and Usable LLMs4Code 24

Towards Safe, Secure, and Usable LLMs4Code

引用

46th international conference on Software engineering: Companion, ICSE-Companion 2024

作者： Al-Kaswan, Ali Delft University of Technology Delft Netherlands

ISBN: (纸本)9798400705021

Large language Models (LLMs) are gaining popularity in the field of natural language processing (NLP) due to their remarkable accuracy in various NLP tasks. LLMs designed for coding are trained on massive datasets, which enables them to learn the structure and syntax of programming languages. These datasets are scraped from the web and LLMs memorise information in these datasets. LLMs for code are also growing, making them more challenging to execute and making users increasingly reliant on external *** aim to explore the challenges faced by LLMs for code and propose techniques to measure and prevent memorisation. Additionally, we suggest methods to compress models and run them locally on consumer hardware. © 2024 IEEE Computer Society. All rights reserved.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Detection of Phishing in Mobile Instant Messaging using natural language processing and Machine Learning 11

Detection of Phishing in Mobile Instant Messaging using Natu...

引用

11th international conference in Software engineering Research and Innovation (CONISOFT)

作者： Verma, Suman Ayala-Rivera, Vanessa Portillo-Dominguez, A. Omar Natl Coll Ireland Sch Comp Dublin Ireland Technol Univ Dublin Sch Business Technol Retail & Supply Chain Dublin Ireland

ISBN: (纸本)9798350328837;9798350328844

Advancements in mobile technology makes it easier to communicate in real time, but at the cost of having a wider potential attack area for phishing. While there has been research in the field related to Email and SMS, Instant Messages lags behind. The widespread usage of instant messengers by individuals of all ages further motivates the addition of software security features in this context. This research aims to detect phishing in mobile instant messages by analysing the language of the message with the help of natural language processing to detect keywords pointing towards phishing. We built the machine learning models using 3 different methods for feature extraction and 3 classification algorithms. Our tests showed that balancing the data with random oversampling increased the classifiers' performance, which were able to achieve an accuracy up to 99.2%.

关键词： Instant Messaging Social engineering Phishing natural language processing Secure Software engineering

来源：评论

学校读者我要写书评

暂无评论

Veracity-Oriented Context-Aware Large language Models-Based Prompting Optimization for Fake News Detection

引用

international JOURNAL OF INTELLIGENT SYSTEMS 2025年第1期2025卷

作者： Jin, Weiqiang Gao, Yang Tao, Tao Wang, Xiujun Wang, Ningwei Wu, Baohai Zhao, Biao Xian Jiaotong Univ XJTU Sch Informat & Commun Engn Xian Shaanxi Peoples R China Anhui Univ Technol AHUT Sch Comp Sci & Technol Maanshan Anhui Peoples R China Shangluo Univ Sch Humanities Shangluo Shaanxi Peoples R China

Fake news detection (FND) is a critical task in natural language processing (NLP) focused on identifying and mitigating the spread of misinformation. Large language models (LLMs) have recently shown remarkable abilities in understanding semantics and performing logical inference. However, their tendency to generate hallucinations poses significant challenges in accurately detecting deceptive content, leading to suboptimal performance. In addition, existing FND methods often underutilize the extensive prior knowledge embedded within LLMs, resulting in less effective classification outcomes. To address these issues, we propose the CAPE-FND framework, context-aware prompt engineering, designed for enhancing FND tasks. This framework employs unique veracity-oriented context-aware constraints, background information, and analogical reasoning to mitigate LLM hallucinations and utilizes self-adaptive bootstrap prompting optimization to improve LLM predictions. It further refines initial LLM prompts through adaptive iterative optimization using a random search bootstrap algorithm, maximizing the efficacy of LLM prompting. Extensive zero-shot and few-shot experiments using GPT-3.5-turbo across multiple public datasets demonstrate the effectiveness and robustness of our CAPE-FND framework, even surpassing advanced GPT-4.0 and human performance in certain scenarios. To support further LLM-based FND, we have made our approach's code publicly available on GitHub (our CAPE-FND code: [Accessed on 2024.09]).

关键词： analogical reasoning bootstrap optimization chain-of-thought fake news detection in-context learning large language models prompt engineering

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：