| Presentation | 2023-10-11 Efficient Automatic Classification of Non-Functional Requirements in Information Systems Using Deep Learning Kazuhiro Mukaida, Seiji Fukui, Takeshi Nagaoka, Takayuki Kitagawa, Shinpei Ogata, Kozo Okano, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recent Advancements in deep learning are increasingly enabling the automation of classifying non-functional requirements in information system requirement specifications. This paper proposes a deep learning-based method that allows even general software engineers to efficiently extract and categorize non-functional requirements from requirement specification documents. Based on the "Non-functional Requirement Grading" framework developed by the Information-technology Promotion Agency (IPA), we incorporated Transformer models such as BERT and GPT-2 into our approach and conducted a comparative analysis with existing methodologies. The results indicate that our proposed method achieves higher accuracy than current methods, underscoring the potential to enhance the consistency of non-functional requirement classification. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Non-Functional Requirements / Requirement Specification / Deep-Learning / CNN / Tranformer / BERT / GPT |
| Paper # | SS2023-23,DC2023-29 |
| Date of Issue | 2023-10-04 (SS, DC) |
| Conference Information | |
| Committee | SS / DC |
|---|---|
| Conference Date | 2023/10/11(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Kozo Okano(Shinshu Univ.) / Tatsuhiro Tsuchiya(Osaka Univ.) |
| Vice Chair | Yoshiki Higo(Osaka Univ.) / Toshinori Hosokawa(Nihon Univ.) |
| Secretary | Yoshiki Higo(Shinshu Univ.) / Toshinori Hosokawa(Tokyo Inst. of Tech.) |
| Assistant | Shinsuke Matsumoto(Osaka Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Software Science / Technical Committee on Dependable Computing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Efficient Automatic Classification of Non-Functional Requirements in Information Systems Using Deep Learning |
| Sub Title (in English) | A Comparative Accuracy Analysis between BERT and GPT-2 |
| Keyword(1) | Non-Functional Requirements |
| Keyword(2) | Requirement Specification |
| Keyword(3) | Deep-Learning |
| Keyword(4) | CNN |
| Keyword(5) | Tranformer |
| Keyword(6) | BERT |
| Keyword(7) | GPT |
| 1st Author's Name | Kazuhiro Mukaida |
| 1st Author's Affiliation | Shinshu University(Shinshu Univ.) |
| 2nd Author's Name | Seiji Fukui |
| 2nd Author's Affiliation | TOSHIBA CORPORATION(TOSHIBA) |
| 3rd Author's Name | Takeshi Nagaoka |
| 3rd Author's Affiliation | TOSHIBA CORPORATION(TOSHIBA) |
| 4th Author's Name | Takayuki Kitagawa |
| 4th Author's Affiliation | TOSHIBA CORPORATION(TOSHIBA) |
| 5th Author's Name | Shinpei Ogata |
| 5th Author's Affiliation | Shinshu University(Shinshu Univ.) |
| 6th Author's Name | Kozo Okano |
| 6th Author's Affiliation | Shinshu University(Shinshu Univ.) |
| Date | 2023-10-11 |
| Paper # | SS2023-23,DC2023-29 |
| Volume (vol) | vol.123 |
| Number (no) | SS-206,DC-207 |
| Page | pp.pp.13-18(SS), pp.13-18(DC), |
| #Pages | 6 |
| Date of Issue | 2023-10-04 (SS, DC) |