检索结果-内蒙古大学图书馆

15th international conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Pandey, Mayank Kunda, Naga Sai Shreya Pranave, K.C. Belwal, Meena Amrita Vishwa Vidyapeetham Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

Coding in a programming language can indeed be a meticulous and a less interesting task, especially when compared to the fluidity of spoken or written communication. Each programming language has its own set of syntax and rules, demanding expertise to effectively write code in it. Through this study, a compiler based approach to translate natural language into Python code is proposed. This endeavor could revolutionize access to programming by making it more intuitive and inclusive. The research involves working with different phases of the compiler including the lexical analyser, syntax and the semantic analyser phase in combination with natural language processing techniques. By automating this process, we aim to streamline programming for a wider audience, removing barriers to entry and making coding more accessible to all. © 2024 IEEE.

关键词： Code Generation Compiler Architecture Compiler-Based Translation natural language processing (NLP) Semantic Understanding

来源：评论

学校读者我要写书评

暂无评论

Detecting Bias in LLMs' natural language Inference Using Metamorphic Testing 24

Detecting Bias in LLMs' Natural Language Inference Using Met...

引用

24th IEEE international conference on Software Quality, Reliability and Security Companion, QRS-C 2024

作者： Li, Zhahao Chen, Jinfu Chen, Haibo Xu, Leyang Guo, Wuhao School of Computer Science & Communication Engineering Jiangsu University Zhenjiang212013 China Jiangsu University Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace Zhenjiang212013 China Asiainfo Security Technology Co. Ltd Nanjing210012 China

ISBN: (纸本)9798350365658

The increasing integration of Large language Mod-els (LLMs) into pivotal decision-making contexts highlights the necessity for rigorous scrutiny to ensure fairness, especially in tasks involving natural language processing (NLP). This paper introduces a novel method employing Metamorphic Testing (MT) to discern bias within the natural language Inference (NLI) task performed by LLMs. Our approach establishes a structured framework for generating test cases using Metamorphic Relations (MRs), incorporating nuanced demographic attributes such as sex, race, occupation, age, and socioeconomic status into textual inputs. We conduct prelimi-nary experiment with 3 common datasets, over 400k test cases in 4 state-of-art LLMs. Through evaluation of model predictions across these MRs, we unveil potential biases indicative of fairness violations. Preliminary investigations conducted with prominent LLMs underscore the effectiveness of our method in illuminating disparities in model performance, thus providing valuable insights into the bias implications of LLMs in NLI tasks. Our method is intuitive and adaptable for other NLP tasks. To the best of our knowledge, this represents the first application of MT to NLI bias detection. © 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

Learning to Balance the Global Coherence and Informativeness in knowledge-Grounded Dialogue Generation 48

Learning to Balance the Global Coherence and Informativeness...

引用

48th IEEE international conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Niu, Chenxu Hu, Yue Peng, Wei Xie, Yuqiang Chinese Academy of Sciences Institute of Information Engineering Beijing China University of Chinese Academy of Sciences School of Cyber Security Beijing China

ISBN: (纸本)9781728163277

Recently, knowledge-grounded dialogue has received increasing interest to render the generated responses with more useful and engaging information. However, the knowledge, locally relevant to the user's utterance, potentially reduces the global coherence of the dialogue. Previous work mainly focuses on retrieving diverse knowledge to assist the response generation whereas resulting in a rough dialogue transition. To alleviate this issue, we propose a History-Adapted knowledge Copy (HAKC) network to adaptively select context-aware knowledge to ensure the coherence of dialogue. Further, we adopt a contrastive learning framework to enhance the knowledge discrimination ability of HAKC. Experimental results demonstrate the outstanding performance of our model on knowledge selection and response generation tasks as well as the boosted generalization. © 2023 IEEE.

关键词： Dialogue Generation Dialogue System knowledge Selection natural language processing

来源：评论

学校读者我要写书评

暂无评论

MIKA: Manager for Intelligent knowledge Access Toolkit for engineering knowledge Discovery and Information Retrieval

引用

INCOSE international Symposium 2023年第1期33卷 1659-1673页

作者： Andrade, Sequoia Walsh, Hannah HX5 - NASA Ames Research Center Mail Stop 269-1 Moffett FieldCA94035-001 United States NASA Ames Research Center Mail Stop 269-1 Moffett FieldCA94035-0001 United States

Repositories of safety reports are often underutilized and only analyzed manually by trained experts, despite safety management systems requiring reports. These collections of documents contain a wealth of information from past projects and operations that could improve system safety and design. Advances in natural language processing techniques have improved information extraction and retrieval in consumer technology, biomedicine, and finance, for instance, but have not been applied to engineering documents on the same scale. To this end, the Manager for Intelligent knowledge Access (MIKA) open-source toolkit has been developed for rapid knowledge discovery and information retrieval in safety engineering applications. The MIKA toolkit uses state-of-the-art natural language processing algorithms and allows a user to apply these methods to their own dataset. This paper describes the MIKA toolkit and its two primary capabilities, knowledge discovery and information retrieval, and demonstrates the toolkit via a case study on National Transportation Safety Board (NTSB) reports. The United States Government retains, and by accepting the article for publication, the publisher acknowledges that the United States Government retains, a non-exclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this work, or allow others to do so, for United States Government purposes. Permission granted to INCOSE to publish and use.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Cartoon Extraction Mechanism via UML Model based on natural language Requirement Specs

Cartoon Extraction Mechanism via UML Model based on Natural ...

引用

international conference on Computational Science and Computational Intelligence (CSCI)

作者： Kim, Janghwan Park, Chansol Jang, Woosung Kim, R. Young Chul Hongik Univ Dept Software & Commun Engn Sejong South Korea

ISBN: (纸本)9798350361513;9798350372304

Recently, research on the development of artificial intelligence, in particular generative AI, has been active around the current world. Recent research mainly focuses on generating various types of outputs (text, image, video, etc.) from natural language textual inputs. However, understanding the meaning of these prompts in AI remains a challenge. In this paper, we propose a mechanism for extracting Cartoon images via UML Models based on natural language-based specifications, mapping a cut image's cartoon elements with UML properties extracted through linguistic textual analysis in software engineering. We expect software engineers to automatically help toon writers generate a cartoon's image with linguistic mechanisms.

关键词： Linguistic Analysis natural language processing Toon Generation UML Diagram Software engineering Design

来源：评论

学校读者我要写书评

暂无评论

Enhancing natural language processing with Deep Learning for Sentiment Analysis 9

Enhancing Natural Language Processing with Deep Learning for...

引用

9th international conference on Science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Om Prakash, C. Kumar, S. Vijaya Pallavi Abbas, Jamal K. Naser, Sarmad Jaafar Haroon, Noor Hanoon School of Management Cmr University 5 Bhuvanagiri OMBR Layout Karnataka Bengaluru560043 India B S Abdur Rahman Crescent Institute of Science And Technology Chennai Tamil Nadu Vandalur India Chaudhary Ranbir Singh University Department of English Haryana Jind India AL-Nisour University College Baghdad Iraq College of Pharmacy National University of Science And Technology DhiQar Iraq Technical Engineering College Al-Ayen University Department of Computer Technical Engineering Thi-Qar Iraq

ISBN: (纸本)9798350365092

natural language processing (NLP) aids in the advancement of intelligent machines through its emphasis on etymologically grounded human-PC connections and a greater understanding of the human language. The demand and necessity to implement information-driven methodologies for automating semantic analysis have increased due to ongoing advancements in processing power and the accessibility of vast quantities of phonetic data. The application of deep learning methods has facilitated significant progress in fields including computer vision, programmed discourse recognition, and natural language processing, which has led to the pervasive adoption of information-driven techniques. This study investigates calculations for unimodal and multimodal sentiment analysis in interpersonal organisations and develops two models, one for message sentiment analysis and the other for picture-message multimodal sentiment analysis in informal communities. The two models demonstrated their electiveness by surpassing the benchmark models by 4.45% and 5.2%, respectively, when evaluated against the current models on distinct datasets. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

ONTOTYPE: Ontology-Guided and Pre-Trained language Model Assisted Fine-Grained Entity Typing 24

ONTOTYPE: Ontology-Guided and Pre-Trained Language Model Ass...

引用

30th ACM SIGKDD conference on knowledge Discovery and Data Mining

作者： Komarlu, Tanay Jiang, Minhao Wang, Xuan Han, Jiawei Univ Illinois Urbana IL 61820 USA Virginia Tech Blacksburg VA USA

ISBN: (纸本)9798400704901

Fine-grained entity typing (FET), which assigns entities in text with context-sensitive, fine-grained semantic types, is a basic but important task for knowledge extraction from unstructured text. FET has been studied extensively in natural language processing and typically relies on human-annotated corpora for training, which is costly and difficult to scale. Recent studies explore the utilization of pre-trained language models (PLMs) as a knowledge base to generate rich and context-aware weak supervision for FET. However, a PLM still requires direction and guidance to serve as a knowledge base as they often generate a mixture of rough and fine-grained types, or tokens unsuitable for typing. In this study, we vision that an ontology provides a semantics-rich, hierarchical structure, which will help select the best results generated by multiple PLM models and head words. Specifically, we propose a novel annotation-free, ontology-guided FET method, ONTOTYPE, which follows a type ontological structure, from coarse to fine, ensembles multiple PLM prompting results to generate a set of type candidates, and refines its type resolution, under the local context with a natural language inference model. Our experiments on the Ontonotes, FIGER, and NYT datasets using their associated ontological structures demonstrate that our method outperforms the state-of-the-art zero-shot fine-grained entity typing methods as well as a typical LLM method, ChatGPT. Our error analysis shows that refinement of the existing ontology structures will further improve fine-grained entity typing.

关键词： Fine-Grained Entity Typing Zero-Shot Entity Typing Masked language Model Prompting natural language Understanding

来源：评论

学校读者我要写书评

暂无评论

Evaluating Recurrent Neural Network Architectures for natural language Understanding 15

Evaluating Recurrent Neural Network Architectures for Natura...

引用

15th international conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Doda, Davendra Kumar Prasad, Koushik V. Pathak, Manoj Kumar Vivekananda Global University Department of Electrical Engineering Jaipur India School of Engineering and Technology Department of Mechanical Engineering Karnataka Bangalore India ARKA JAIN University Department of English Jharkhand Jamshedpur India

ISBN: (纸本)9798350370249

This paper examines and evaluates the effectiveness of recurrent neural network (RNN) architectures for natural language knowledge. The paper starts by imparting historical data on recurrent neural networks and their software to various responsibilities. It then goes on to talk about diverse RNN architectures, such as lengthy quick-time period reminiscence (LSTM), Gated Recurrent Unit (GRU) and Bonior Recurrent Neural network (BONN). The paper then focuses on the efficacy of each RNN structure for textual content expertise obligations. A sequence of experiments is carried out to degree the overall performance of the one-of-a-kind fashions, the use of 3 preferred datasets-Wiki text, Squad and IMDB, as well as two newly created datasets. The paper analyses the empirical consequences of the various RNN architectures and finds that LSTM fashions are normally satisfactory performers, although BONN architectures can also be aggressive in some cases. The paper additionally looks at numerous techniques to enhance performance, which include pre-processing and hyper-parameter tuning. The paper concludes that, whilst RNN architectures are powerful for herbal language know-how responsibilities, the exact architecture and parameters can also need to be chosen cautiously, relying on the project and dataset to hand. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Judicial Speech Summarization Tool 15

Judicial Speech Summarization Tool

引用

15th international conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Geetha, N. Sanjushree, S. Dharshini, Priya M. Sneha, R. Atria Institute of Technology CSE Karnataka Bengaluru India

ISBN: (纸本)9798331300579

Audio-to-text summary entails turning spoken knowledge into brief written summaries to help in effective information retrieval and *** an oral argument in court In audio, spoken legal discourse is condensed into a brief written form yet important details and ideas are maintained for effective understanding and *** oral argument records must be summarized in order to conduct case analysis, legal research, and transparency all *** speeches are condensed so that legal professionals can swiftly grasp and recollect important *** research investigates the critical steps involved in precisely and concisely transcription of a complicated legal argument from *** both academics and legal professionals, accurate transcribing of legal discourse is *** research investigates these methodologies, from state-of-the-art natural language processing (NLP) software to conventional transcription *** emphasizes how crucial this technology is to ensuring courtroom transparency, enhancing case analysis, and speeding up legal *** research contributes to a revolution in the understanding and accessibility of legal knowledge at a time when legal technology is undergoing rapid *** project focuses on producing the transcript and summary of the court oral argument audio. © Grenze Scientific Society, 2024.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Defect Correction Method for Software Requirements Text Using Large language Models

Defect Correction Method for Software Requirements Text Usin...

引用

international Joint conference on Neural Networks (IJCNN)

作者： Zhang, Li Ouyang, Liubo Xu, Zhuoqun Hunan Univ Coll Comp Sci & Elect Engn Changsha Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Text defect correction holds a pivotal role within the domain of text processing. In the face of the rapid advancement of natural language processing (NLP) technologies, significant challenges persist in achieving precision and efficiency, particularly within specialized domains such as software requirements. For instance, traditional methods require labor-intensive verification, and the generative Large language Models(LLMs) paradigm suffers from illusions and knowledge deficits. So for professional software requirement text and defect correction processing, we construct a Chinese requirement text defect corpus containing 215 Chinese requirement texts and 10,049 manually labeled sentences and propose a contextual prompt pattern based on LLMs, which mainly includes the following steps: (1) Requirements text defect detection classification using fine-tuned BERT. (2) Extracting primary key information from requirement text using fine-tuned UIE. (3) The above results are embedded as contextual information in extensible prompt templates, respectively, and defects are corrected by interacting with generative LLMs. The experimental results show that by utilizing prompt learning and in-context learning techniques for requirement text defect correction, we achieved an outstanding improvement (30.3%) in defect correction effectiveness.

关键词： prompt learning large language models software requirements

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：