Presentation 2021-09-16
Performance Validation of Pre-Trained BERT in the Financial Domain
Masahiro Suzuki, Hiroki Sakaji, Masanori Hirano, Kiyoashi Izumi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, general-purpose language models pre-trained on large corpora such as BERT have been widely used. In Japanese, several pre-trained models based on Wikipedia have been published. On the other hand, general-purpose models may not be sufficiently effective in the financial domain because of the use of specialized phrases. In this study, we construct a pre-training model using a corpus of the financial domain, and evaluate it on a task in the financial domain.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Natural language processing / Language resources / BERT / Financial text
Paper # NLC2021-12
Date of Issue 2021-09-09 (NLC)

Conference Information
Committee NLC
Conference Date 2021/9/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) The 18th Text Analytics Symposium
Chair Kazutaka Shimada(Kyushu Inst. of Tech.)
Vice Chair Mitsuo Yoshida(Univ. of Tsukuba) / Takeshi Kobayakawa(NHK)
Secretary Mitsuo Yoshida(Univ. of Tokyo) / Takeshi Kobayakawa(Hiroshima Univ. of Economics)
Assistant Kanjin Takahashi(Sansan) / Ko Mitsuda(NTT)

Paper Information
Registration To Technical Committee on Natural Language Understanding and Models of Communication
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Performance Validation of Pre-Trained BERT in the Financial Domain
Sub Title (in English)
Keyword(1) Natural language processing
Keyword(2) Language resources
Keyword(3) BERT
Keyword(4) Financial text
1st Author's Name Masahiro Suzuki
1st Author's Affiliation The University of Tokyo(The Univ. of Tokyo)
2nd Author's Name Hiroki Sakaji
2nd Author's Affiliation The University of Tokyo(The Univ. of Tokyo)
3rd Author's Name Masanori Hirano
3rd Author's Affiliation The University of Tokyo(The Univ. of Tokyo)
4th Author's Name Kiyoashi Izumi
4th Author's Affiliation The University of Tokyo(The Univ. of Tokyo)
Date 2021-09-16
Paper # NLC2021-12
Volume (vol) vol.121
Number (no) NLC-178
Page pp.pp.26-29(NLC),
#Pages 4
Date of Issue 2021-09-09 (NLC)