Zobrazeno 1 - 10
of 67
pro vyhledávání: '"KIYOTAKA UCHIMOTO"'
Publikováno v:
Journal of Natural Language Processing. 29:748-753
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::89c61cf59b108ba7ad9a3bfe98a38a8c
https://doi.org/10.5715/jnlp.29.748
https://doi.org/10.5715/jnlp.29.748
Publikováno v:
Journal of Natural Language Processing. 21:379-401
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::798a2c81f421e26816de1112e1206adf
https://doi.org/10.5715/jnlp.21.379
https://doi.org/10.5715/jnlp.21.379
Publikováno v:
Computational Intelligence. 28:426-451
Dependency parsing has attracted considerable interest from researchers and developers in natural language processing. However, to obtain a high-accuracy dependency parser, supervised techniques require a large volume of hand-annotated data, which ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b14763dd4ca9859cb85869a8bb61f1b3
https://doi.org/10.1111/j.1467-8640.2012.00451.x
https://doi.org/10.1111/j.1467-8640.2012.00451.x
Autor:
Kentaro Torisawa, Qing Ma, Kouichi Doi, Yasuhiko Watanabe, Ryo Nishimura, Masaki Murata, Masao Utiyama, Kiyotaka Uchimoto
Publikováno v:
Cognitive Computation. 2:272-279
The maximum entropy (ME) method is a powerful supervised machine learning technique that is useful for various tasks. In this paper, we introduce new studies that successfully employ ME for natural language processing (NLP) problems including machine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::92d52750ae732234fc49899f17fa1690
https://doi.org/10.1007/s12559-010-9046-3
https://doi.org/10.1007/s12559-010-9046-3
Autor:
Takuya Matsuzaki, Jun'ichi Tsujii, Yao-zhong Zhang, Kun Yu, Kiyotaka Uchimoto, Yusuke Miyao, Xiangli Wang
Publikováno v:
Journal of Natural Language Processing. 17:61-80
Comparing with the traditional way of manually developing grammar based on linguistic theory, corpus-oriented grammar development is more promising. To develop HPSG grammar through the corpus-oriented way, a treebank is an indispensable part. This pa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::340407da7945dc0a69d4954af5818aa6
https://doi.org/10.5715/jnlp.17.3_61
https://doi.org/10.5715/jnlp.17.3_61
Publikováno v:
ACM Transactions on Asian Language Information Processing. 8:1-20
Dependency parsing has become increasingly popular for a surge of interest lately for applications such as machine translation and question answering. Currently, several supervised learning methods can be used for training high-performance dependency
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fcb8060646f321112020217ff1545443
https://doi.org/10.1145/1568292.1568293
https://doi.org/10.1145/1568292.1568293
Autor:
Yiou Wang, Kentaro Torisawa, Hitoshi Isahara, Kiyotaka Uchimoto, Canasai Kruengkrai, Jun'ichi Kazama
Publikováno v:
IEICE Transactions on Information and Systems. :2298-2305
In this paper, we present a discriminative word-character hybrid model for joint Chinese word segmentation and POS tagging. Our word-character hybrid model offers high performance since it can handle both known and unknown words.We describe our strat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d01a031668fc54bee6513ec5eca8b66
https://doi.org/10.1587/transinf.e92.d.2298
https://doi.org/10.1587/transinf.e92.d.2298
Publikováno v:
Language Resources and Evaluation. 40:233-242
This paper describes experiments carried out utilizing a variety of machine-learning methods (the k-nearest neighborhood, decision list, maximum entropy, and support vector machine), and using six machine-translation (MT) systems available on the mar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::54e05af0ad75def0234e7d4b5828f299
https://doi.org/10.1007/s10579-007-9022-z
https://doi.org/10.1007/s10579-007-9022-z
Autor:
Suguru Matsuyoshi, Seiichi Nakagawa, Toshihiro Takagi, Satoshi Sato, Takehito Utsuro, Kiyotaka Uchimoto, Masatoshi Tsuchiya, Takao Shime
Publikováno v:
Journal of Natural Language Processing. 14:111-138
日本語には, 複数の語がひとかたまりとなって, 全体として1つの機能的な意味を持つ表現が多数存在する.このような表現は機能表現と呼ばれ, 日本語文の構造を理解するために非常に重
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::db7c4ff7cb74f36c3c1db1fb320ffca7
https://doi.org/10.5715/jnlp.14.111
https://doi.org/10.5715/jnlp.14.111
Publikováno v:
ACM Transactions on Asian Language Information Processing. 4:18-37
In recent years, various types of tagged corpora have been constructed and much research using tagged corpora has been done. However, tagged corpora contain errors, which impedes the progress of research. Therefore, the correction of errors in corpor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5949857192fc09c257428e8fd75b17c6
https://doi.org/10.1145/1066078.1066080
https://doi.org/10.1145/1066078.1066080