Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Hanawa, Kazuaki"'
Autor:
Kato, Sumi1,2 (AUTHOR) katoh@aomoricgu.ac.jp, Hanawa, Kazuaki3 (AUTHOR), Saito, Manabu4 (AUTHOR), Nakamura, Kazuhiko1 (AUTHOR)
Publikováno v:
PLoS ONE. 9/27/2024, Vol. 19 Issue 9, p1-29. 29p.
In this paper, we explore the capacity of a language model-based method for grammatical error detection in detail. We first show that 5 to 10% of training data are enough for a BERT-based error detection method to achieve performance equivalent to a
Externí odkaz:
http://arxiv.org/abs/2108.12216
Autor:
Fujii, Ryo, Mita, Masato, Abe, Kaori, Hanawa, Kazuaki, Morishita, Makoto, Suzuki, Jun, Inui, Kentaro
Neural Machine Translation (NMT) has shown drastic improvement in its quality when translating clean input, such as text from the news domain. However, existing studies suggest that NMT still struggles with certain kinds of input with considerable no
Externí odkaz:
http://arxiv.org/abs/2011.02121
Explaining the predictions made by complex machine learning models helps users to understand and accept the predicted outputs with confidence. One promising way is to use similarity-based explanation that provides similar instances as evidence to sup
Externí odkaz:
http://arxiv.org/abs/2006.04528
Autor:
Tagami, Tsubasa, Ouchi, Hiroki, Asano, Hiroki, Hanawa, Kazuaki, Uchiyama, Kaori, Suzuki, Kaito, Inui, Kentaro, Komiya, Atsushi, Fujimura, Atsuo, Yanai, Hitofumi, Yamashita, Ryo, Machino, Akinori
We present a new task, suspicious news detection using micro blog text. This task aims to support human experts to detect suspicious news articles to be verified, which is costly but a crucial step before verifying the truthfulness of the articles. S
Externí odkaz:
http://arxiv.org/abs/1810.11663
We present in this paper our approach for modeling inter-topic preferences of Twitter users: for example, those who agree with the Trans-Pacific Partnership (TPP) also agree with free trade. This kind of knowledge is useful not only for stance detect
Externí odkaz:
http://arxiv.org/abs/1704.07986
Autor:
Kato, Sumi1,2 (AUTHOR) katoh@aomoricgu.ac.jp, Hanawa, Kazuaki3,4 (AUTHOR), Linh, Vo Phuong5 (AUTHOR), Saito, Manabu1,6 (AUTHOR), Iimura, Ryuichi7 (AUTHOR), Inui, Kentaro3,4 (AUTHOR), Nakamura, Kazuhiko1,6 (AUTHOR)
Publikováno v:
PLoS ONE. 2/25/2022, Vol. 18 Issue 2, p1-28. 28p.
Publikováno v:
Proceedings of the 31st Pacific Asia Conference on Language, Information and Computation. :336-345
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=jairo_______::0b81cdb827af55e9cf089db9ec3e8d0b
http://hdl.handle.net/2065/00058454
http://hdl.handle.net/2065/00058454