The purpose of this study was to identify the availability of authoring tools that support vertical flow function based upon empirical experiments. There were five EPUB authoring tools selected for this study. Four ma...The purpose of this study was to identify the availability of authoring tools that support vertical flow function based upon empirical experiments. There were five EPUB authoring tools selected for this study. Four major editing procedures were designed for the project. The first was the support of Chinese character input. The second was vertical form editing. The third was ruby position editing, and finally, testing whether the editing software was capable of outputting a document as an e-Book in EPUB 3.0 format. Five programs were tested, and only one of the five was able to fulfill the aforementioned requirements. The usability of each program is positively verified through this study.展开更多
针对传统文本匹配方法无法学习文本间深度语义匹配特征,深度短文本匹配模型难以捕获长文本细粒度匹配信号等问题,提出一种面向长文本的两阶段文本匹配模型TP-TM(Two-Phase Text Matching)。首先使用句子级过滤器过滤噪声句并提取关键句...针对传统文本匹配方法无法学习文本间深度语义匹配特征,深度短文本匹配模型难以捕获长文本细粒度匹配信号等问题,提出一种面向长文本的两阶段文本匹配模型TP-TM(Two-Phase Text Matching)。首先使用句子级过滤器过滤噪声句并提取关键句,然后将所获关键句输入词语级过滤器,利用融入了改进版删减策略的BERT(Bidirectional Encoder Representations from Transformers)模型挖掘文本间深度交互特征,对关键句进行词语级噪声过滤和细粒度匹配操作,最终通过拼接BERT不同位置特征预测文本对关系。在中文长文本公开新闻数据集CNSE(Chinese News Same Event)和CNSS(Chinese News Same Story)上进行实验,结果显示,相较于基线模型,TP-TM模型在CNSE和CNSS数据集上的准确率分别提升了0.99和1.55个百分点,F1值分别提升了0.98和1.46个百分点,有效提升了长文本匹配任务的准确度。展开更多
为全面优化Web前端界面综合性能,保障各个功能模块间良好通信,提升前端界面运行流畅性,本研究将超文本标记语言第5版本(Hyper Text Markup Language,HTML5)应用于Web前端开发中。对HTML5在Web前端开发中的应用现状进行分析,并深度探究We...为全面优化Web前端界面综合性能,保障各个功能模块间良好通信,提升前端界面运行流畅性,本研究将超文本标记语言第5版本(Hyper Text Markup Language,HTML5)应用于Web前端开发中。对HTML5在Web前端开发中的应用现状进行分析,并深度探究Web前端系统和HTML5关键技术之后,进一步融合模型、视图、控制(Model-View-Controller,MVC)开发模式,构建基于基础视图层、核心逻辑层、数据模型层的数据可视化(Data Visualization Layout,DVL)框架。以此实现在服务器端、前后端之间的有效通信;完善Web前端界面与响应指令的直接连接;促进前端场景有效集成与渲染;建立Web前端表单,保障前端展示信息的完善性。展开更多
文摘The purpose of this study was to identify the availability of authoring tools that support vertical flow function based upon empirical experiments. There were five EPUB authoring tools selected for this study. Four major editing procedures were designed for the project. The first was the support of Chinese character input. The second was vertical form editing. The third was ruby position editing, and finally, testing whether the editing software was capable of outputting a document as an e-Book in EPUB 3.0 format. Five programs were tested, and only one of the five was able to fulfill the aforementioned requirements. The usability of each program is positively verified through this study.
文摘针对传统文本匹配方法无法学习文本间深度语义匹配特征,深度短文本匹配模型难以捕获长文本细粒度匹配信号等问题,提出一种面向长文本的两阶段文本匹配模型TP-TM(Two-Phase Text Matching)。首先使用句子级过滤器过滤噪声句并提取关键句,然后将所获关键句输入词语级过滤器,利用融入了改进版删减策略的BERT(Bidirectional Encoder Representations from Transformers)模型挖掘文本间深度交互特征,对关键句进行词语级噪声过滤和细粒度匹配操作,最终通过拼接BERT不同位置特征预测文本对关系。在中文长文本公开新闻数据集CNSE(Chinese News Same Event)和CNSS(Chinese News Same Story)上进行实验,结果显示,相较于基线模型,TP-TM模型在CNSE和CNSS数据集上的准确率分别提升了0.99和1.55个百分点,F1值分别提升了0.98和1.46个百分点,有效提升了长文本匹配任务的准确度。
