检索结果-内蒙古大学图书馆

ieee international conference on Web Services (ieee ICWS)

作者： Qu, Yutong Yang, Jian Zhang, Wei Emma Chen, Weitong Yu, Hong Qing Univ Adelaide Adelaide SA Australia Macquarie Univ Sydney NSW Australia Univ Derby Derby England

ISBN: (纸本)9798350368567;9798350368550

With the prompt growth of digital data, a newly evolving economy has shown its development trend in today's data-driven world, which is known as the data economy. Stimulating this data economy and seizing benefits from it remains an open question. This paper delves into feasible breakthroughs prompting this emerging data economy in supplying data catalogue services for data products. Accordingly, the opportunities and potential for the application of natural language processing technology in data catalogues are envisaged, corresponding to challenges posed by various types of data assets. By exploring the state-of-the-art natural language processing fields, this paper introduces the latest advancements in knowledge-aware natural language processing for contributing to data catalogues.

关键词： Data Catalogue Data Product Date Economy natural language processing knowledge

来源：评论

学校读者我要写书评

暂无评论

A Seamless ChatGPT knowledge Plug-in for the Labour Market

引用

ieee ACCESS 2024年 12卷 155821-155837页

作者： Alonso, Ruben Dessi, Danilo Meloni, Antonello Murgia, Marco Recupero, Diego Reforgiato Scarpi, Giuseppe R2M Solut Srl I-27100 Pavia Italy Univ Politecn Madrid Ctr Automat & Robot CSIC Programa Doctorado Madrid 28500 Spain Univ Sharjah Coll Comp & Informat Dept Comp Sci Sharjah U Arab Emirates Univ Cagliari Dept Math & Comp Sci I-09124 Cagliari Italy

In today's rapidly evolving labor market, the emergence of new roles and the decline of traditional ones have led to a complex landscape of job titles and skill requirements. This complexity often causes ambiguity and confusion, affecting both novices and experienced professionals. To address this, extensive international efforts have produced reference databases of jobs and skills, such as ESCO and O*NET. However, the challenge remains to make this information easily accessible and interpretable for users with varying levels of expertise. To address the challenge above, this paper introduces a knowledge Plug-in for ChatGPT, designed to serve as an intuitive, user-friendly interface between workers and these authoritative databases. By harnessing the power of natural language processing (NLP), the plug-in enables a seamless question-answering experience, effectively masking the underlying complexity with a carefully engineered architecture. Furthermore, generative AI enhances the user experience by providing relevant information in domains extending beyond the traditional scope of employment. An initial user study demonstrates the plug-in's effectiveness in improving the usability and accuracy of job-related queries. We detail the development, architecture, and validation of this innovative tool, highlighting its potential impact on the future of employment search and career development.

关键词： Chatbots Databases Semantics Recruitment engineering profession Taxonomy Structured Query language Social networking (online) Resumes Employment Large language models natural language processing knowledge based systems Professional aspects Question answering (information retrieval) Query processing Conversational agents labor market large language models natural language processing occupational databases

来源：评论

学校读者我要写书评

暂无评论

Exploring Sensory knowledge and Pre-training language Models for Chinese Metaphor Detection

Exploring Sensory Knowledge and Pre-training Language Models...

引用

28th international conference on Asian language processing (IALP)

作者： Zhao, Qingqing Xiang, Xue Wang, Zhongqing Chinese Acad Social Sci Inst Linguist Beijing Peoples R China Soochow Univ Sch Comp Sci & Technol Suzhou Peoples R China

ISBN: (纸本)9798331540869;9798331540852

processing of metaphorical languages has been one of the most challenging tasks in natural language processing (NLP). Recent work utilizing neural models has received notable results on metaphor detection. However, the characteristic of metaphorical languages showing an intimate relationship with sensory experiences has not been given enough attention in NLP. This study proposes an innovative model for the task of Chinese metaphor detection by incorporating the conceptual knowledge of sensory experiences into a neural network model. Experiments show that our model outperforms the state-of-the-art baseline models significantly, hence contributing to the ongoing efforts to incorporate neuro-cognitive data in NLP tasks. In addition, the effectiveness of our model helps to deepen our understanding of metaphor that sensory experiences form the crucial part of the embodied nature of metaphorical languages.

关键词： Metaphor detection Sensory experiences Neural network model Mandarin Chinese

来源：评论

学校读者我要写书评

暂无评论

Distilled BERT Model In natural language processing 14

Distilled BERT Model In Natural Language Processing

引用

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

作者： Vakili, Yazdan Zandiye Fallah, Avisa Sajedi, Hedieh School of Mathematics Statistics and Computer Science University of Tehran Tehran Iran

ISBN: (纸本)9798331511272

This paper reviews the evolution of natural language processing (NLP) models, concentrating on the distillation techniques used to create efficient and compact versions of large models. Traditional NLP models laid the foundation but had limitations in scalability and contextual understanding. Transformer models like BERT revolutionized NLP but required significant computational resources. This review examines TinyBERT, DistilBERT, MobileBERT, and MiniLM, which balance size and performance through knowledge distillation. These distilled models deliver robust performance while being optimized for use on devices with limited computational resources, enabling the application of advanced NLP features in practical scenarios. ©2024 ieee.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Construction of Intelligent Educational Teaching Evaluation System Based on knowledge Graph and natural language processing 2

Construction of Intelligent Educational Teaching Evaluation ...

引用

2nd ieee international conference on Sensors, Electronics and Computer engineering, ICSECE 2024

作者： Lin, Lin Shandong Vocational College of Science and Technology Weifang China

ISBN: (数字)9798350373646

ISBN: (纸本)9798350373646

This project constructs a subject knowledge map for instructional design based on natural language processing technology. This provides a new way of thinking and method for the teaching practice of this subject. Firstly, the ontology-oriented dictionary learning method is studied. By using the fusion ontology relation extraction method, the subject-action-semantic association is extracted to enrich the category of association. Ontology alignment technique is used to disambiguate the extracted knowledge base. Using 'Neo4j' as the development tool, the knowledge map of course design theme is displayed visually. It is found that presenting the image of information and knowledge in the subject teaching is an operable technological support. The system further expands the applied research field. knowledge graph and other visual tools will be used in more education fields in the future to achieve specific visual education based on the corresponding experience and lessons. © 2024 ieee.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Structuring natural language Requirements with Large language Models 32

Structuring Natural Language Requirements with Large Languag...

引用

32nd ieee international Requirements engineering conference (RE)

作者： Norheim, Johannes J. Rebentisch, Eric MIT Dept Aeronaut & Astronaut Cambridge MA 02139 USA MIT Sociotech Syst Res Ctr 77 Massachusetts Ave Cambridge MA 02139 USA

ISBN: (纸本)9798350395525;9798350395518

Structured requirements have long been proposed to improve the quality of requirements while facilitating downstream applications like modeling. Nevertheless, in practice, adopting structures such as templates and semi-formal logic imposes additional training and expertise constraints, limiting their wider adoption. In this paper, we investigate the application of natural language processing (NLP) to translate natural language requirements into structured representations. Existing methodologies have been reported for specific formalisms or requirement types. In this research preview, we go beyond the state-of-the-art by generalizing to generic templates and semiformal logic. Specifically, we investigate the application of a state-of-the-art pre-trained large language model (LLM), GPT-4. We show preliminary evidence that this new technology can translate natural language requirements to a target template or semi-formal language based on as little as one translation example, as long as the example captures the same structure as the translated requirement. We observe this behavior across three formalisms: a requirements template structure (EARS), a custom minimalistic requirements modeling language for system performance requirements, and a semi-formal structure for linear temporal logic (LTL). We propose a rigorous way to investigate how well these observations are generalized based on this preliminary evidence.

关键词： Large language Models natural language processing Requirements Translation Requirements Modeling

来源：评论

学校读者我要写书评

暂无评论

Research on Distributional Compositional Categorical Model in Both Classical and Quantum natural language processing 27

Research on Distributional Compositional Categorical Model i...

引用

27th ieee/ACIS international conference on Software engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)

作者： Liu, Tingyu Wei, Yingying Wang, Jingtao Commun Univ China State Key Lab Media Convergence & Commun Sch Comp & Cyber Sci Beijing Peoples R China

ISBN: (纸本)9798350391961;9798350391954

language models based on neural network primarily focus on learning patterns and representations from the input data, without explicitly modeling the grammatical structure of the text, thus often lacks of the consideration of syntax information. The distributional compositional categorical (DisCoCat) model is a framework that can both capture the distributional information of words and the syntactic structure of sentence. Thus, we research the application of DisCoCat models in both quantum and classical natural language processing. Specifically, in classical and quantum natural language processing, we respectively converted sentences into tensor networks and quantum circuits based on the DisCoCat model to get representation containing both semantic and syntactic information of language in classical and quantum computer. We conduct experiment for a text binary classification task in both classical and quantum natural language processing setting to verify the effectiveness of DisCoCat model. The experimental results shown that the combination of DisCoCat with quantum computing has significant potential.

关键词： DisCoCat QNLP text representation

来源：评论

学校读者我要写书评

暂无评论

Linguistic Intelligence in Large language Models for Telecommunications 59

Linguistic Intelligence in Large Language Models for Telecom...

引用

59th Annual ieee international conference on Communications (ieee ICC)

作者： Ahmed, Tasnim Piovesan, Nicola De Domenico, Antonio Choudhury, Salimur Queens Univ Sch Comp Kingston ON Canada Huawei Technol Paris Res Ctr Boulogne France

ISBN: (纸本)9798350304060;9798350304053

Large language Models (LLMs) have emerged as a significant advancement in the field of natural language processing (NLP), demonstrating remarkable capabilities in language generation and other language-centric tasks. Despite their evaluation across a multitude of analytical and reasoning tasks in various scientific domains, a comprehensive exploration of their knowledge and understanding within the realm of natural language tasks in the telecommunications domain is still needed. This study, therefore, seeks to evaluate the knowledge and understanding capabilities of LLMs within this domain. To achieve this, we conduct an exhaustive zero-shot evaluation of four prominent LLMs-Llama-2, Falcon, Mistral, and Zephyr. These models require fewer resources than ChatGPT, making them suitable for resource-constrained environments. Their performance is compared not only with state-of-the-art, fine-tuned models but also with larger LLMs such as GPT-3.5 and GPT-4. To the best of our knowledge, this is the first work to extensively evaluate and compare the understanding of LLMs across multiple language-centric tasks in this domain. Our evaluation reveals that zero-shot LLMs can achieve performance levels comparable to the current state-of-the-art fine-tuned models. This indicates that pretraining on extensive text corpora equips LLMs with a degree of specialization, even within the telecommunications domain. We also observe that no single LLM consistently outperforms others, and the performance of different LLMs can fluctuate. Although their performance lags behind fine-tuned models, our findings underscore the potential of LLMs as a valuable resource for understanding various aspects of this field that lack large annotated data.

关键词： Large language Models natural language processing Telecommunications Zero-Shot Evaluation Classification Summarization Question Answering

来源：评论

学校读者我要写书评

暂无评论

Biomedical Relation Extraction using LLMs and knowledge Graphs 10

Biomedical Relation Extraction using LLMs and Knowledge Grap...

引用

ieee 10th international conference on Big Data Computing Service and Machine Learning Applications (ieee BigDataService)

作者： Chellagurki, Pranav Kuniarti, Sai Prasanna Kumar Peela, Rahul Raghava Yeluri, Neeharika Rojas, Carlos Jetcheva, Jorjeta San Jose State Univ Comp Engn Dept San Jose CA 95192 USA

ISBN: (纸本)9798350366396;9798350366389

Due to the rapid growth of research papers on biomedical topics, it has become increasingly important to make advancements in biomedical natural language processing (NLP). Biomedical NLP enables us to extract important information from text, such as new insights into the role of different genes in disease susceptibility, or the potential for drug therapies that are effective against one disease to work effectively against another. In this paper, we present a comparative evaluation of the binary relation classification capabilities of the current state-of-the-art binary relation classifier, BioBERT, against recently released open-source large language models, Gemma-2b, Gemma-7b, and Llama2-7b, which we fine-tune with the benchmark GAD and EU-ADR datasets. In addition, we quantify the potential of discovering new relationships by utilizing knowledge graphs built out of known binary relations.

关键词： relation extraction biomedical natural language processing biomedical natural language processing LLMs

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and natural language processing for Quality Control and Management

Artificial Intelligence and Natural Language Processing for ...

引用

ieee international conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)

作者： Xie, Haiyan Sally Gandla, Sai Ram Bhattacharya, Mangolika Solanki, Pranshoo Zheng, Dingnan Illinois State Univ Dept Technol Normal IL 61761 USA Illinois State Univ Normal IL 61761 USA Univ Illinois Champaign IL USA

ISBN: (纸本)9798350322996;9798350323009

Established engineering standards are facing challenges in adapting to the evolution of novel material properties, designing entirely new materials, and uncovering new mechanisms that transcend intuitive understanding. This research aims to investigate a new framework of domain-specific language models to automatically generate feasible engineering designs based on requirements. The work is anchored in the understanding of natural language processing and the fidelity requirements of machine-learning models for the civil and construction engineering domain. Relevant reports from the Transportation Research Information Service and standard specifications from various departments of transportation were included in the data collection. Another dataset was the summarized literature of 36 highway agencies. After the comparison of Support Vector Machines (SVM), Long Short-Term Memory network, and linear regression, the SVM algorithm was implemented in the framework to support decision-making through textual and tabular communication, and the results showed improvements in accuracy (130%) and F1 Score (65%). In this research, utilizing case-based content extraction alongside reliable statistical uncertainty estimation has shown the potential to generate valuable decision-support tools and recommendation systems for both engineers and managers. The applications encompassing textual content extraction alongside reliable statistical uncertainty estimation demonstrate the potential to create valuable decision-support tools and recommendation systems for engineers and managers.

关键词： Domain-Specific natural language processing Reliability Concrete Construction knowledge Management

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：