检索结果-内蒙古大学图书馆

3rd international conference on Electronics Technology and Artificial Intelligence, ETAI 2024

作者： Wang, Bing Department of Information Engineering Shandong Water Conservancy Vocational College Shandong Rizhao China

ISBN: (纸本)9781510683143

Driven by natural language processing technology, topic models have shown a wide range of application value in fields such as text analysis, classification and clustering. The GSDMM topic model has been widely recognized in the field of topic modeling due to its ability to automatically infer the number of clusters, fast convergence, and efficient processing of sparse and high-dimensional short texts. This paper aims to explore the text evaluation research based on natural language processing and GSDMM (Gibbs Sampling and Distributed Memory Model) topic model, and carries out relevant practice in the text evaluation of project-based teaching course. © 2024 SPIE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Fusion of Stance Labels and Event knowledge for Effective Stance Detection 6

Fusion of Stance Labels and Event Knowledge for Effective St...

引用

6th international conference on natural language processing (ICNLP)

作者： Yin, Zhaoning Zhang, Yuanshuo Li, Aohua Chen, Bo Zhao, Xiaobing Minzu Univ China Sch Informat Engn Natl Language Resource Monitoring & Res Ctr Minor Beijing Peoples R China

ISBN: (纸本)9798350349122;9798350349115

Stance detection on social media has attracted significant attention recently. However, for a hot event, it is not easy to determine the stance of a comment on a given target, because there is complex comment-target-event-stance relationship behind it. To alleviate this problem, a new fusion method is proposed, which integrates explicit stance label and brief event background into BERT-based stance classifier. By fine-tuning the BERT model, it learns to reason about accurate stances based on the fused information. Experiments on a Weibo stance detection dataset demonstrate the effectiveness of the method.

关键词： Stance detection stance label event BERT

来源：评论

学校读者我要写书评

暂无评论

An Interactive Approach for Query-based Multi-Document Scientific Text Summarization 14

An Interactive Approach for Query-based Multi-Document Scien...

引用

14th international conference on Computer and knowledge engineering, ICCKE 2024

作者： Nejati, Mohammadsadra Ahmadi, Abbas Mohebi, Azadeh Dept. of Industrial Engineering Amirkabir University of Technology Tehran Iran Tehran Iran

ISBN: (纸本)9798331511272

The overwhelming volume of scientific documents necessitates automatic summarization to assist researchers in efficiently finding relevant data, making informed decisions, and retrieving appropriate answers to their queries. Query-based automatic summarization is to provide a textual summary related to user’s initial query. Most of the previous approaches in query-based summarization, only consider the user’s initial query to model user’s information need, and rarely rely on additional interaction between user and system. This study proposes an interactive multi-document summarization system designed to assist researchers in processing scientific documents. The interactive approach is necessary to refine document selection and improve summary relevance through user feedback. The system utilizes advanced natural language processing techniques to retrieve and summarize relevant content, including query-based summarization to tailor summaries to specific user queries. By incorporating user-generated questions, the system enhances the coherence and pertinence of summaries. The system is tested and evaluated for Persian language. Despite the lack of labeled datasets in the Persian, the proposed approach demonstrates effective summarization through unsupervised methods. User evaluations confirm the system’s potential to significantly improve information retrieval and comprehension in scientific research. © 2024 IEEE.

关键词： Structured Query language

来源：评论

学校读者我要写书评

暂无评论

GAEL: A Global-Aware Entity Linking Model Based on Retriever-Reader Paradigm 7

GAEL: A Global-Aware Entity Linking Model Based on Retriever...

引用

7th international conference on Machine Learning and natural language processing, MLNLP 2024

作者： Wang, Linjie Hao, Shiyi Lu, Yuxing Wang, Chen Liu, Yunfei Li, Shengyang Technology and Engineering Center for Space Utilization Chinese Academy of Sciences Beijing China Key Laboratory of Space Utilization Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Tencent AI Lab Shenzhen China

ISBN: (纸本)9798350354973

The field of space science and applications, rich in domain knowledge, has witnessed research on domain knowledge extraction and the preliminary construction of domain knowledge graphs. Entity linking serves as a fundamental component for intelligent applications of knowledge graphs. Recently, the retriever-reader paradigm, inspired by question-answering tasks, has advanced the development of entity linking. However, the existing studies overlook the relationships between entities, resulting in the lack of global consistency in the predictions. Furthermore, they struggle to deal with redundant entities effectively. We propose a Global-Aware Entity Linking Model (GAEL) to address these issues. GAEL employs incremental training during model training, integrating linking results in successive rounds. By incorporating the entity information predicted in previous rounds into new training inputs, GAEL continuously optimizes semantic information and strengthens interactions between candidate entities, which helps to identify potential entities corresponding to mentions. Besides, GAEL utilizes a novel entity screening mechanism that encodes candidate entities and input text separately and ranks them based on semantic similarity, effectively resolving the issue of multiple entities corresponding to the same mention. Experimental results demonstrate that GAEL significantly improves entity linking performance on datasets in the field of space science and applications, as well as on multiple public datasets. © 2024 IEEE.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large language Models for Automated knowledge Acquisition in Personal Health Status Evaluation 24

Leveraging Large Language Models for Automated Knowledge Acq...

引用

8th international conference on natural language processing and Information Retrieval, NLPIR 2024

作者： Fu, Zhen-Xin Lee, Chung-Hong DEPARTMENT OF ELECTRICAL ENGINEERING National Kaohsiung University of Science and Technology Kaohsiung Taiwan

ISBN: (纸本)9798400717383

Healthcare issues have always been regarded as an important application area of artificial intelligence research. When an individual's physical abnormality occurs without sufficient medical knowledge, it often becomes more serious because it is not treated immediately and correctly, especially in remote areas where medical resources are scarce. Motivated by this, in this study we developed a personal healthcare assistant system which integrates Large language Models (LLMs) to assess users' health status and provide appropriate assistance and advice. Users interact with the system by describing the discomfort they are experiencing. Based on these descriptions, the system matches symptoms with diseases using a similarity comparison from a hospital dataset. It selects the 20 most relevant conditions as the basis for the model's few-shot learning and then employs Instruction Learning to tailor the model for this assessment task. This system lets users understand the possible diseases corresponding to their symptoms preliminarily and follow the system's instructions for timely and appropriate treatment. Additionally, this study evaluates the performance of various LLMs, such as GPT-4, Llama3, and TAIDE models. We assess the models based on thousands of interactions between the system and users, comparing the applicability and differences of different models. Experimental results demonstrate that the proposed system can achieve the basic functions of personal health monitoring and assessment of health status. © 2024 Copyright held by the owner/author(s).

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Optimizing High-Dimensional Text Embeddings in Emotion Identification: A Sliding Window Approach 16

Optimizing High-Dimensional Text Embeddings in Emotion Ident...

引用

16th international conference on knowledge Discovery and Information Retrieval, KDIR 2024 as part of 16th international Joint conference on knowledge Discovery, knowledge engineering and knowledge Management, IC3K 2024

作者： Uymaz, Hande Aka Metin, Senem Kumova Izmir University of Economics Department of Software Engineering Izmir Turkey

ISBN: (纸本)9789897587160

natural language processing (NLP) is an interdisciplinary field that enables machines to understand and generate human language. One of the crucial steps in several NLP tasks, such as emotion and sentiment analysis, text similarity, summarization, and classification, is transforming textual data sources into numerical form, a process called vectorization. This process can be grouped into traditional, semantic, and contextual vectorization methods. Despite their advantages, these high-dimensional vectors pose memory and computational challenges. To address these issues, we employed a sliding window technique to partition high-dimensional vectors, aiming not only to enhance computational efficiency but also to detect emotional information within specific vector dimensions. Our experiments utilized emotion lexicon words and emotionally labeled sentences in both English and Turkish. By systematically analyzing the vectors, we identified consistent patterns with emotional clues. Our findings suggest that focusing on specific sub-vectors rather than entire high-dimensional BERT vectors can capture emotional information effectively, without performance loss. With this approach, we examined an increase in pairwise cosine similarity scores within emotion categories when using only sub-vectors. The results highlight the potential of the use of sub-vector techniques, offering insights into the nuanced integration of emotions in language and the applicability of these methods across different languages. © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Epistemology for Cyber Security: A Controlled natural language Approach 6th

Epistemology for Cyber Security: A Controlled Natural Langua...

引用

6th international conference on Information and knowledge Systems (ICIKS)

作者： Chase, Leigh Mohasseb, Alaa Aziz, Benjamin Univ Portsmouth Sch Comp Portsmouth Hants England

ISBN: (纸本)9783031516634;9783031516641

In this paper we introduce a new Controlled natural language (CNL) known as "Noam". It is used to express cyber security knowledge and for reasoning over it. The approach follows examples set by other domain-specific languages and constrained grammars, but is highly unusual due to its singular focus on cyber security. Like most CNLs Noam is both human-readable and machine-solvable, thus fulfilling important assurance requirements with respect to transparency and explainability. The language seeks to address a growing problem faced by security engineers and architects;namely, that their endeavours are constrained by the complexity and sheer interconnectedness of the systems they protect. This is further compounded by year-on-year vulnerability disclosure rates and diversification of the Tactics, Techniques and Procedures used by threat actors. Our approach is analogical in which the Noam CNL is used to construct a system model, instrument it with data from the real environment and apply functional programming techniques in order to 'solve-for' certain conditions of interest. The intention is to demonstrate the value of CNLs and semantic reasoning within cyber security, framed in the context of improving the information available to security engineers, architects and other decision-makers.

关键词： cyber security knowledge representation controlled natural language epistemology machine reasoning explainable learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Techniques for Chinese Image Captioning: Investigating Attention Mechanisms Based on Object Detection for Chinese Image Caption Generation 5

Advanced Techniques for Chinese Image Captioning: Investigat...

引用

5th international conference on Machine Learning and Computer Application, ICMLCA 2024

作者： Hua, Yongbin Li, Pei'ang Zeng, Xiangjin Xu, Hong School of Computer Science and Engineering Wuhan Institute of Technology Hubei Wuhan China

ISBN: (纸本)9798331530334

The task of image caption generation aims to automatically produce natural language descriptions that match the content of images, integrating the fields of machine vision and natural language processing, which holds significant theoretical and practical value. Inspired by top-down attention mechanisms, this paper proposes an innovative attention model. Utilizing the output of pretrained object detection networks as prior knowledge for images, the model guides the generation of natural language descriptions. By directly incorporating the results of object detection as attention inputs into the text generation network, the model effectively focuses on key descriptive regions of images, thereby significantly enhancing performance. On public Chinese image captioning datasets, this model demonstrates substantial advantages in metrics such as BLEU-4 and METEOR. © 2024 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

natural language processing Techniques for Advancing Materials Discovery: A Short Review

引用

international JOURNAL OF PRECISION engineering AND MANUFACTURING-GREEN TECHNOLOGY 2023年第5期10卷 1337-1349页

作者： Lee, Joo Hyuk Lee, Myeonghun Min, Kyoungmin Soongsil Univ Sch Mech Engn 369 Sangdo Ro Seoul 06978 South Korea Soongsil Univ Sch Syst Biomed Sci 369 Sangdo Ro Seoul 06978 South Korea

In the development of new industries, there is a growing demand for innovative materials. However, locating such materials is a laborious and time-consuming endeavor. In response, there has been a shift toward studying new materials more efficiently using existing material science research knowledge. There has been an increase in the number of materials science-related papers over the past two decades, and attempts to use them for research purposes have increased as the methods have been systematized. Past research papers, for instance, can be used to predict new materials or obtain optimal synthesis parameters for materials with the desired properties. In this movement, natural language processing (NLP) is a crucial technology. In the past decade, NLP has emerged as one of the most rapidly expanding areas of artificial intelligence, proving to be a valuable tool for processing language-based data. In this review, we will examine how NLP is used in the materials science literature, what processes it can be used for, and the primary NLP technologies currently in use, with a particular focus on specific use cases. We will also discuss this approach's limitations.

关键词： natural language processing Text mining Information extraction Materials discovery

来源：评论

学校读者我要写书评

暂无评论

KGLM-QA: A Novel Approach for knowledge Graph-Enhanced Large language Models for Question Answering 15

KGLM-QA: A Novel Approach for Knowledge Graph-Enhanced Large...

引用

15th international conference on Information and knowledge Technology, IKT 2024

作者： Safaei, Alireza Akhavan Saboori, Pegah Ramezani, Reza Nematbakhsh, Mohammadali Department of Software Engineering University of Isfahan Isfahan Iran

ISBN: (纸本)9798331522254

Large language models excel in various natural language processing tasks but often struggle with knowledge-intensive queries, particularly those involve rare entities or require precise factual information. This paper presents a novel framework that enhances capabilities of an LLM-based question answering system by incorporating structured knowledge from knowledge graphs. Our approach employs entity extraction, semantic similarity scoring, and adaptive graph exploration to efficiently navigate and extract relevant information from knowledge graphs. The core of the presented solution is a knowledge graph-enhanced language model process that iteratively refines subgraph exploration and answer generation, complemented by a fallback mechanism for robustness across diverse question types. Experiments on location-based questions from the Entity Questions dataset demonstrate significant improvements in the quality of responses. Using the Gemini 1.5 Flash model, our system achieved an accuracy increase from 36% to 71% for partially correct answers and from 22% to 69% for exactly correct answers, as evaluated by human assessors. This approach offers a promising direction for developing more reliable and accurate question answering systems, particularly for queries involving long-tail entities or specific factual knowledge. © 2024 IEEE.

关键词： knowledge graph

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：