計量的分析のための15世紀朝鮮語形態素解析済みコーパス構築：仏教諺解を対象に

构建 15 世纪韩语词法语料库以进行定量分析：以佛教谚语为目标

• 批准号: 20K00558
• 负责人: 須賀井 義教
• 金额: $ 1.75万
• 依托单位: Kindai University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2020
• 资助国家: 日本
• 起止时间: 2020-04-01 至 2024-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-20K00558/
• 关键词: 朝鮮語史; コーパス; 形態素解析; 計量的分析; TEIガイドライン; TEI; 言語学; コーパス言語学; 朝鮮語学

計画の3年目である令和4年度にも，引き続きMeCab（めかぶ）向けの15世紀朝鮮語形態素解析用辞書である「MkHanDic」に，辞書項目の追加を行った．現在の辞書項目数は9730項目で，学習用データは3070文である．解析の精度について，やはり同音異義語の判定に問題があり，解決方法について検討を行っている．ただし，これまでの作業を通じて，辞書の項目数を着実に増やしており，さらに登録項目を増やしていくことで，全体的な精度を向上させることが可能である．引き続き，辞書項目と学習用データを増やしていく．また，形態素解析を行う前段階の作業として，TEI（Text Encoding Initiative）ガイドラインを用いた電子データの整備を並行して行っているが，今年度は『般若心経諺解』『救急簡易方諺解』の電子データ構築に着手した．これらの文献も15世紀に刊行されたものであるが，本研究で対象とする『月印釈譜』とはテキストの構造，構成がやや異なる．様々なタイプの文献について，TEIガイドラインによる電子データ化を行うことで，知見がより深まり，『月印釈譜』に対する電子データ化もさらに精緻さを加えることが可能になると考える．また，形態素解析の結果も盛り込んだ電子データ化の方法についても，今後検討する予定である．今後はこれらのデータを元に，本研究の研究対象である『月印釈譜』の他の巻についても電子データ化を行い，作業が終了したデータから形態素解析を行って，未登録の項目を辞書項目として追加する作業を行う．

The 3-year and 4-year MeCab is introduced to the 15th century. The word "MkHanDic" is added to the lexical item. Now the number of lexical items is 9730, and the academic language is 3070. The accuracy is analyzed, and the homonym is used to determine the problem. The number of entries is related to the number of entries, and the number of entries. In the first phase of the industry, TEI (Text Encoding Initiative) has used electronic equipment and equipment to carry out this year's "Prajna Heart solution" and "Emergency purchase solution". This year, we have started to do business in the first part of this year. This year, we have started to do business in the first part of this year. The 15th world publication of the medical literature has been published The purpose of this study is to improve the quality of the industry. The results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study are as follows: in this study, the results of this study The results of computer analysis show that the computer simulation method is effective, and the future is expected. In the future, we are going to change the price of the computer. In this study, we are interested in computer science, computer science, computer science and computer science. If you do not sign up for an unregistered project, please add an additional job line for the unregistered project.

项目成果

中期朝鮮語の計量的分析の試み―クラスター分析による『釈譜詳節』各巻の分類―

尝试对中古朝鲜语进行定量分析：使用聚类分析对《Shafu Shosettsu》各卷进行分类。

• 发表时间: 2022
• 期刊: 朝鮮語研究
• 作者: 木下瞳;林炫情;須賀井義教;斉藤信浩・林炫情・淺尾仁彦・李在鎬・須賀井義教;李在鎬;李在鎬;Yoshihiko Asao;水野淳太・淺尾仁彦;須賀井 義教
• 通讯作者: 須賀井 義教

中期朝鮮語の計量的分析の試み

中朝鲜语定量分析的尝试

• DOI: 10.50986/koreanlinguistics.9.0_175
• 发表时间: 2022
• 期刊: Journal of the Society for Korean Linguistics in Japan
• 作者: 山森良枝;荻野千砂子;Hiroshi Aoyagi;須賀井 義教
• 通讯作者: 須賀井 義教

「MeCab で韓国語」

“MeCab 韩国菜”

MeCab用形態素解析辞書MkHanDic

MeCab 的形态分析词典 MkHanDic