Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Kanako Komiya"'
Publikováno v:
Computational Linguistics (2023)
Externí odkaz:
https://doaj.org/article/2e51ef802df7474da25f8132f71dab0d
Publikováno v:
Computational Linguistics (2022)
Externí odkaz:
https://doaj.org/article/24170fc9a2f549f7bab6caeff3b97c1e
Publikováno v:
ACM Transactions on Asian and Low-Resource Language Information Processing. 22:1-22
In recent years, the use of distributed representations has been a fundamental technology for natural language processing. However, Japanese has multiple compound words, and often we must compare the meanings of a word and a compound word. Moreover,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb15033a546635fd6deab34cb76bdd47
https://doi.org/10.1145/3561299
https://doi.org/10.1145/3561299
Publikováno v:
言語資源ワークショップ発表論文集 = Proceedings of Language Resources Workshop. 1:59-69
Tokyo University of Agriculture and Technology
National Institute for Japanese Language and Linguistics
会議名: 言語資源ワークショップ2022, 開催地: オンライン, 会期: 2022年8月30日-31日, 主催: 国立国語研究
National Institute for Japanese Language and Linguistics
会議名: 言語資源ワークショップ2022, 開催地: オンライン, 会期: 2022年8月30日-31日, 主催: 国立国語研究
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=jairo_______::626c724c700ac06c355c4be05a1d41ff
http://id.nii.ac.jp/1328/00003724/
http://id.nii.ac.jp/1328/00003724/
Autor:
Jun Izutsu, Kanako Komiya
Publikováno v:
International Journal on Natural Language Computing. 11:29-45
This study proposes a method to develop neural models of the morphological analyzer for Japanese Hiragana sentences using the Bi-LSTM CRF model. Morphological analysis is a technique that divides text data into words and assigns information such as p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c6ed8c1b52dbf9a9b7c7565f9bcef74b
https://doi.org/10.5121/ijnlc.2022.11103
https://doi.org/10.5121/ijnlc.2022.11103
Publikováno v:
Journal of Natural Language Processing. 29:854-874
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6fb045389ffd2cbb9d7339d50676c6f1
https://doi.org/10.5715/jnlp.29.854
https://doi.org/10.5715/jnlp.29.854
Publikováno v:
BASE-Bielefeld Academic Search Engine
application/pdf
Ibaraki University
National Institute for Japanese Language and Linguistics
In this paper, we show how to use bilingual word embeddings (BWE) to automatically create a corresponding table of meaning tags from two dictio
Ibaraki University
National Institute for Japanese Language and Linguistics
In this paper, we show how to use bilingual word embeddings (BWE) to automatically create a corresponding table of meaning tags from two dictio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::274e55824bc8d7d2535721a3a076f885
https://repository.ninjal.ac.jp/records/3085
https://repository.ninjal.ac.jp/records/3085
Autor:
Jun Izutsu, Kanako Komiya
This study proposes a method to develop neural models of the morphological analyzer for Japanese Hiragana sentences using the Bi-LSTM CRF model. Morphological analysis is a technique that divides text data into words and assigns information such as p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41e4cfa4cf5c020414516ff5e91823e8
Autor:
Mika Kishino, Kanako Komiya
Publikováno v:
Natural Language Processing.
This study extracted and analyzed the linguistic speech patterns that characterize Japanese anime or game characters. Conventional morphological analyzers, such as MeCab, segment words with high performance, but they are unable to segment broken expr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c98977228ec8e5ee2d3102872c2843dc
https://doi.org/10.5121/csit.2021.112307
https://doi.org/10.5121/csit.2021.112307
Publikováno v:
BASE-Bielefeld Academic Search Engine
application/pdf
茨城大学
国立国語研究所
Ibaraki University
National Institute for Japanese Language and Linguistics
All-words word-sense disambiguation (all-words WSD) involves identifying the senses of all words i
茨城大学
国立国語研究所
Ibaraki University
National Institute for Japanese Language and Linguistics
All-words word-sense disambiguation (all-words WSD) involves identifying the senses of all words i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::75272360b0225523e32f6a65a817c879
https://repository.ninjal.ac.jp/records/2255
https://repository.ninjal.ac.jp/records/2255