云南高校图书馆联盟文献共享服务平台- TEXT

检索规则说明：AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：范例一： (K=图书馆学 OR K=情报学) AND A=范并思　　　　范例二：J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual

全部期刊核心期刊 EI来源期刊 SCI来源期刊 CA来源期刊 CSCD来源期刊 CSSCI来源期刊

Joint Generation of Distractors for Multiple-Choice Questions:A Text-to-Text Approach: 《Computers, Materials & Continua》2025年第5期1683-1705,共23页Ricardo Rodriguez-Torrealba Eva Garcia-Lopez Antonio Garcia-Cabot; supported by the Universidad de Alcalá(UAH)under Grant PIUAH21/IA-010;Comunidad Autonóma de Madrid under Grant CM/JIN/2021-034.; Generation of good-quality distractors is a key and time-consuming task associated withmultiple-choice questions(MCQs),one of the assessment items that have dominated the educational field for years.Recent advances in...; 关键词：Text-to-text distractor generation fine-tuning FlanT5 LongT5 multiple-choice QUESTIONNAIRE

Heimtextil 2025:以纺织连接世界: 《纺织导报》2025年第2期79-82,共4页张娜; 2025年法兰克福国际家用及商用纺织品展览会(Heimtextil 2025)于1月14—17日在德国法兰克福举行,在为期4天的展会期间,来自全球142个国家及地区的展商与观众到场参与,进一步巩固了Heimtextil作为全球首屈一指的家用及商用纺织品与纺织...; 关键词：德国法兰克福 TEXT 纺织品展会 HE

A Novel CAPTCHA Recognition System Based on Refined Visual Attention: 《Computers, Materials & Continua》2025年第4期115-136,共22页Zaid Derea Beiji Zou Xiaoyan Kui Monir Abdullah Alaa Thobhani Amr Abdussalam; supported by the National Natural Science Foundation of China(Nos.U22A2034,62177047);High Caliber Foreign Experts Introduction Plan funded by MOST,and Central South University Research Programme of Advanced Interdisciplinary Studies(No.2023QYJC020).; Improving website security to prevent malicious online activities is crucial,and CAPTCHA(Completely Automated Public Turing test to tell Computers and Humans Apart)has emerged as a key strategy for distinguishing huma...; 关键词：Text-based CAPTCHA recognition refined visual attention web security computer vision

利用T5和MAML的多语种英语翻译质量改进研究: 《鄂州大学学报》2025年第2期98-102,105,共6页梅玲孙红萍; 安徽省职业与成人教育学会2023年教育教学研究规划课题(AZCJ2023229);2022年安徽职业技术学院校级科技工程人文社科项目(2022xjrs010);2023年度安徽省社会科学创新发展研究课题(2023KY006)。; 为改善翻译效果与质量,结合T5 (Text-To-Text Transfer Transformer)和MAML (Model-Agnostic Meta-Learning),对其在多语种英语翻译中的质量可持续改进与应用进行了研究。采用自回归学习方法,对T5模型预训练参数进行微调,构建一个生成...; 关键词：多语言英语翻译 Text-To-Text Transfer Transformer Model-Agnostic Meta-Learning 英语翻译模型

基于关键词抽取和提示学习的藏语新闻稿件生成方法: 《信息化研究》2025年第2期35-42,共8页完玛道吉安见才让; 青海民族大学2023年度校级本硕博(学生)项目阶段性成果(No.09M2023003)。; 本文提出了一种新的藏语新闻稿件生成方法,结合改进的TextRank算法进行关键词抽取和基于提示学习的输入模板设计。实验对比了LLaMa2-7B和BaiChuan2-13B两种大规模语言模型在基线和增强配置下的性能。结果显示,BaiChuan2-13B增强模型在B...; 关键词：抽取提示学习大规模语言模型 TextRank算法

Developing a novel assistive technology,empowering the deaf to speak,using visual feedback.: 《Journal of Otology》2025年第1期12-19,共8页Singh S Nagarajan K Chachan R Pandey P Vijayalakshmi P Verma N Singh A; Background:Profoundly deaf children beyond 5 years of age and deaf adults with no prior access to hearing have limited options to learn oral speech.They rely mainly on sign language for communication.This is because,i...; 关键词：DEAFNESS sign language cochlear implants speech to text deaf rehabilitation deaf speech

面向研究生招生咨询的中文Text-to-SQL模型: 《计算机工程》2025年第3期362-368,共7页王庆丰李旭姚春龙程腾腾; 辽宁省教育厅青年科技人才“育苗”项目(J2020113);辽宁省教育厅科学研究项目(LJKZ0537);2024年度辽宁省属本科高校基本科研业务费专项资金资助项目(LJ212410152070)。; 研究生招生咨询是一种具有代表性的短时间高频次问答应用场景。针对现有基于词向量等方法的招生问答系统返回答案不够精确,以及每年需要更新问题库的问题,引入了基于文本转结构化查询语言(Text-to-SQL)技术的RESDSQL模型,可将自然语言...; 关键词：中文文本转结构化查询语言自然语言查询中文SQL语句生成预训练模型 Text-to-SQL数据集

A Dual-Layer Attention Based CAPTCHA Recognition Approach with Guided Visual Attention: 《Computer Modeling in Engineering & Sciences》2025年第3期2841-2867,共27页Zaid Derea Beiji Zou Xiaoyan Kui Alaa Thobhani Amr Abdussalam; supported by the National Natural Science Foundation of China(Nos.U22A2034,62177047);High Caliber Foreign Experts Introduction Plan funded by MOST,and Central South University Research Programme of Advanced Interdisciplinary Studies(No.2023QYJC020).; Enhancing website security is crucial to combat malicious activities,and CAPTCHA(Completely Automated Public Turing tests to tell Computers and Humans Apart)has become a key method to distinguish humans from bots.Whil...; 关键词：Text-based CAPTCHA image recognition guided visual attention web security computer vision

ControlVideo:conditional control for one-shot text-driven video editing and beyond: 《Science China(Information Sciences)》2025年第3期146-158,共13页Min ZHAO Rongzhen WANG Fan BAO Chongxuan LI Jun ZHU; supported by National Natural Science Foundation of China(Grant Nos.62061136001,61620106010,62076145,U19B2034,U1811461,U19A2081,6197222);Beijing Outstanding Young Scientist Program(Grant No.BJJWZYJH012019100020098);Tsinghua Institute for Guo Qiang;High Performance Computing Center,Tsinghua University;Major Innovation&Planning Interdisciplinary Platform for the“Double-First Class”Initiative,Renmin University of China;Fundamental Research Funds for the Central Universities;the Research Funds of Renmin University of China(Grant No.22XNKJ13);supported by XPlorer Prize;sponsored by Beijing Nova Program(Grant No.20220484044);supported by Shuimu Tsinghua Scholar。; This paper presents ControlVideo for text-driven video editing—generating a video that aligns with a given text while preserving the structure of the source video.Building on a pre-trained text-to-image diffusion mod...; 关键词：diffusion models controllable generation text-driven editing video editing long video editing

Comparing Large Language Models for Generating Complex Queries: 《Journal of Computer and Communications》2025年第2期236-249,共14页Limin Ma Ken Pu Ying Zhu Wesley Taylor; This study presents a comparative analysis of a complex SQL benchmark, TPC-DS, with two existing text-to-SQL benchmarks, BIRD and Spider. Our findings reveal that TPC-DS queries exhibit a significantly higher level of...; 关键词：Text-to-SQL Evaluation LLM Generative AI

TEXT