All-words Word Sense Disambiguation in Japanese using Local Context
Project/Area Number |
15K16046
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Intelligent informatics
|
Research Institution | Ibaraki University |
Principal Investigator |
Komiya Kanako 茨城大学, 理工学研究科(工学野), 講師 (10592339)
|
Research Collaborator |
Suzuki Rui 茨城大学, 工学部, 学生
|
Project Period (FY) |
2015-04-01 – 2019-03-31
|
Project Status |
Completed (Fiscal Year 2018)
|
Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2015: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
Keywords | 語義曖昧性解消 / 教師なし学習 / All-words / all-words / 語義 / 分散表現 / all-word / 日本語 |
Outline of Final Research Achievements |
We developed an unsupervised algorithm to identify the meaning of every word in a corpus. The target language is Japanese. We used surrounding word vectors, which are the word embeddings generated via deep learning method and synonyms of the target words.
|
Academic Significance and Societal Importance of the Research Achievements |
日本語を対象としたall-wordsの語義曖昧性解消(文中の全ての単語を対象として単語が辞書のどの意味を持っているのかを同定するタスク)を行う仕組みを提案した.文例集と正解を与えなくても語義曖昧性解消を行う仕組みを提案することができた. また,この際に使うディープ・ラーニング技術の適切なパラメータや繰り返し回数についても実験によって明らかにした.
|
Report
(5 results)
Research Products
(56 results)