Presentation | 2022-09-13 Extraction of sentences representing company-specific competitive advantages from integrated reports Yuta Sugawara, Hiroyuki Sakai, Kengo Enami, Kaito Takano, Kei Nakagawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this research, we propose a method for extracting sentences representing company-specific competitive advantages from integrated reports by deep learning. For example, our method extracts sentences that include the company's strengths, specific management strategies, and business development such as “The automotive products business of the Sumitomo Science & Engineering Group handles anti-vibration rubber and automotive hoses, which boast the largest market share in the world, as well as interior and sound insulation products that contribute to ride comfort and safety.”. Form these sentences, it is possible to understand a company's unique strengths and the points in which the company is superior among companies in the same industry. Our method uses BERT as a classifier with fine tuning, so that even a small amount of training data can be classified with a reasonably high accuracy. In addition, our method restricts the classification results by the degree of similarity between sentences, and attained 0.713 precision. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | integrated reports / sentence identification / machine learning / clue phrases / information extraction |
Paper # | NLC2022-7 |
Date of Issue | 2022-09-06 (NLC) |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2022/9/13(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Keio Univ. Yagami Campus. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | The 19th Text Analytics Symposium |
Chair | Mitsuo Yoshida(Univ. of Tsukuba) |
Vice Chair | Hiroki Sakaji(Univ. of Tokyo) / Takeshi Kobayakawa(NHK) |
Secretary | Hiroki Sakaji(NTT) / Takeshi Kobayakawa(Hiroshima Univ. of Economics) |
Assistant | Kanjin Takahashi(Sansan) / Yasuhiro Ogawa(Nagoya Univ.) |
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) | Extraction of sentences representing company-specific competitive advantages from integrated reports |
Sub Title (in English) | |
Keyword(1) | integrated reports |
Keyword(2) | sentence identification |
Keyword(3) | machine learning |
Keyword(4) | clue phrases |
Keyword(5) | information extraction |
1st Author's Name | Yuta Sugawara |
1st Author's Affiliation | Seikei University(Seikei) |
2nd Author's Name | Hiroyuki Sakai |
2nd Author's Affiliation | Seikei University(Seikei) |
3rd Author's Name | Kengo Enami |
3rd Author's Affiliation | Seikei University(Seikei) |
4th Author's Name | Kaito Takano |
4th Author's Affiliation | Nomura Asset Management Co.(Nomura Asset Management) |
5th Author's Name | Kei Nakagawa |
5th Author's Affiliation | Nomura Asset Management Co.(Nomura Asset Management) |
Date | 2022-09-13 |
Paper # | NLC2022-7 |
Volume (vol) | vol.122 |
Number (no) | NLC-180 |
Page | pp.pp.13-18(NLC), |
#Pages | 6 |
Date of Issue | 2022-09-06 (NLC) |