Development of a Concordance-Making System Utilizing an Optical Character Reader

利用光学字符阅读器开发索引制作系统

• 批准号: 62450054
• 负责人: HIDA Yoshifumi
• 金额: $ 3.97万
• 依托单位: National Language Research Institute
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for General Scientific Research (B)
• 财政年份: 1987
• 资助国家: 日本
• 起止时间: 1987 至 1988
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-62450054/
• 关键词: OCR; Concordance; 『尋常小学国語読本』; 『尋常小学国語読』

The purpose of this study is to develop a system for an efficient making of a concordance by using an optical character reader (OCR).An OCR reads and identifies hand-written characters on worksheets including Katakana. Alphabet, figures, and other symbols and feed them into a computer. It can process information written on worksheets such as word units, entry words, parts of speech, homonym Id codes, etc.The next chosen for this study is that of the "Jinjoo Shoogaku Kokugo Tokuhon" or state-compiled elementary school readers used nationwide from 1918 to 1938. The text includes a total of about 100,000 words.Following word has been completed during the two-year period. (1)Word unit identification for each entry word. (2)Input of style information such as spoken, written, dialog, and verse to each quotation by OCR worksheets. (3)Input of data such as entry words, parts of speech, and homonym ID by OCR worksheets. (4)Readout by the OCR. (5)Correction of data. (6)Programming for processing revised data. (7)Programming for KWIC output. (8)Printout of KWIC lists.

这项研究的目的是开发一种系统，通过使用光学字符阅读器(OCR)来高效地创建匹配。光学字符阅读器读取并识别包括片假名在内的工作表上的手写字符。字母、数字和其他符号，并将它们输入计算机。它可以处理写在工作表上的信息，如单词单位、词条、词性、谐音ID代码等。本研究的下一个选择是1918年至1938年在全国范围内使用的国家汇编的小学阅读器《JINJO Shoogaku Kokugo Tokuhon》。正文共约10万字。以下文字已在两年时间内完成。(1)每个条目单词的单词单位标识。(2)通过OCR工作表将口语、书面语、对话、诗句等风格信息输入到每个引文中。(3)通过OCR工作表录入词条、词类、同音异义词ID等数据。(4)OCR读数。(5)数据的修正。(6)修正数据处理程序设计。(7)KWIC输出编程。(8)KWIC列表打印输出。