Machine-Aided Writing System based on Super-Function and Intellectual Corpus

基于超函数和智能语料库的机器辅助写作系统

• 批准号: 14380166
• 负责人: FUJI Ren
• 金额: $ 4.74万
• 依托单位: The University of Tokushima
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 2002
• 资助国家: 日本
• 起止时间: 2002 至 2005
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-14380166/
• 关键词: Machine Translation; Information Retrieval; Knowledge System; Intellectual Corpus; Super-Function; Machine-Aided Writing System; Artificial Intelligence; Association; コーパス; 知能化; 関連

With the rapid development of the Internet, writing English becomes indispensable work for computer users all over the world. Especially, it is necessary to make sending the science and technology thesis from Japan using English, but native-English writing is difficult for most Japanese users. Therefore, the research and development of the system that supports the writing English is important.To build a machine-aided system that helps non-native users not only on spelling checking and grammar checking but also on writing native sentences using the expression way of native-English is a challenging issue.In our project, a new function, Machine-Aided Writing Function, is proposed. Our methodology can deal with any foreign languages, but we only focus on how to construct a Machine-Aided English Writing system for Japanese users in the project. The basic idea of the method we proposed is based on Super-Function means and intellectual Corpus. SF is a new concept that we presented to develop multi-lingual machine translation.A Japanese English bilingual corpus was built and the super-function base used in the Machine-Aided Writing system has been extracted. The construction methodology for building a Machine-Aided Writing system has been studied and a prototype Machine Aiding English Writing system has been constructed based on the proposed method. Some experiments using the prototype system have been carried out and the results show the proposed method is effective.

随着互联网的快速发展，英语写作成为全世界计算机用户不可缺少的工作。尤其是从日本发来的科技论文要用英语，但以英语为母语的写作对大多数日本用户来说是困难的。因此，研究和开发支持英语写作的系统具有重要意义。构建一个既能帮助非母语用户进行拼写检查和语法检查，又能帮助非母语用户使用母语英语表达方式书写母语句子的机器辅助系统是一个具有挑战性的问题。我们的方法可以处理任何外语，但我们只专注于如何在项目中为日语用户构建一个机器辅助英语写作系统。该方法的基本思想是基于超函数方法和智能语料库。语料库是我们为开发多语种机器翻译而提出的一个新概念。我们建立了一个日英双语语料库，并提取了机器辅助写作系统中使用的超函数库。研究了机器辅助写作系统的构建方法，并在此基础上构建了一个机器辅助英语写作系统原型。利用原型系统进行了实验，结果表明该方法是有效的。

项目成果

Specific Speaker's Japanese Speech Corpus over Long and Short Time Periods

特定说话人的长、短时间段日语语音语料库

• 发表时间: 2006
• 期刊: Journal of Research on Computing Science Vol.17
• 作者: Satoru Tsuge;Masami Shishibori;Fuji Ren;Kenji Kita;Shingo Kuroiwa
• 通讯作者: Shingo Kuroiwa

Robust Feature Extraction in a Variety of Input Devices on the Basis of ETSI Standard DSR Front-end

基于ETSI标准DSR前端的多种输入设备的鲁棒特征提取

• 发表时间: 2002
• 期刊: 7th International Conference on Spoken Language Processing (ICSLP2002)
• 作者: K.Z.Liu;M.Q.Dao;T.Inoue;Satoru Tsuge
• 通讯作者: Satoru Tsuge

Realizing Face-to-Face Interaction by View-based Tracking

通过基于视图的跟踪实现面对面交互

• 发表时间: 2002
• 期刊: International Journal of Information Technology and Decision Making 1・2
• 作者: Mohamed Fattah;Fuji Ren;Shingo Kuroiwa;Alsayed Atlam;Hongbin Zhu;Fuji Ren;Fuji Ren;台暁英;Xiaoying Tai;Taihao Li;Shunji Mituyoshi;Fuji Ren;Fuji Ren;Taihao Li;Arthur B. Smith;Satoru Tsuge;Shingo Kuroiwa;Satoru Tsuge;Kouji Tanaka;Manabu Sasayama;Tomoyuki Kagawa;Minoru Nagayasu;Zhao Xin;Fuji Ren;Qiang Zhou;Fuji Ren;Xiaoying Tai;Shigang Li
• 通讯作者: Shigang Li

Ding Lin: "Automatic Evaluation of Sentence Fluency"IEEE International Conference on Systems, Man and Cybernetics. 1687-1692 (2003)

丁林：“句子流畅性的自动评估”IEEE系统、人与控制论国际会议。

XML based Extended Super-function Schema in Knowledge Representation

知识表示中基于XML的扩展超功能模式

• 发表时间: 2005
• 期刊: Research on Computing Science 16・1
• 作者: Xin Zhao;Fuji Ren;Shingo Kuroiwa;Mohamed Abdel Fattah;黒岩 眞吾;Qiong Liu
• 通讯作者: Qiong Liu