| Presentation | 2023-03-18 An Experimental Analysis of Sub-tasks for Multi-task Learning-based Text Classification Yusuke Kimura, Takahiro Komamizu, Kenji Hatano, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Multi-task learning, in which a phrase extraction such as key phrase extraction and named entity extraction is chosen for a sub-task, has shown improvements for the accuracy of text classification. However, multi-task learning requires extra annotations for sub-tasks in addition to the annotation for the mainstream text classification task. That extra annotation incurs extra human and financial costs, which are typically not small. These costs are therefore a barrier to the practical application of multi-task learning. To deal with this issue, the authors conducted research on realizing sub-tasks by automatic labeling for sub-tasks using a heuristic method, and confirmed that it improved classification accuracy. Although the previous findings can be widely applicable to other heuristic-based labeling methods to create sub-tasks, their availability has not been discussed. In addition, the requirements that such sub-tasks should satisfy have not been revealed. Therefore, this study attemps to clarify the requirements for improving the accuracy of text classification by using generic subtasks in multi-task learning. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | text classification / Subword-phrase / Sub-task |
| Paper # | NLC2022-26 |
| Date of Issue | 2023-03-11 (NLC) |
| Conference Information | |
| Committee | NLC / IPSJ-NL |
|---|---|
| Conference Date | 2023/3/18(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | OIST |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Applications of natural language processing, and etc. |
| Chair | Mitsuo Yoshida(Univ. of Tsukuba) / 須藤 克仁(奈良先端科学技術大学院大学) |
| Vice Chair | Hiroki Sakaji(Univ. of Tokyo) / Takeshi Kobayakawa(NHK) |
| Secretary | Hiroki Sakaji(NTT) / Takeshi Kobayakawa(Hiroshima Univ. of Economics) / (LINE株式会社) |
| Assistant | Kanjin Takahashi(Sansan) / Yasuhiro Ogawa(Nagoya Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Natural Language |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | An Experimental Analysis of Sub-tasks for Multi-task Learning-based Text Classification |
| Sub Title (in English) | |
| Keyword(1) | text classification |
| Keyword(2) | Subword-phrase |
| Keyword(3) | Sub-task |
| 1st Author's Name | Yusuke Kimura |
| 1st Author's Affiliation | Doshisha University(Doshisha Univ.) |
| 2nd Author's Name | Takahiro Komamizu |
| 2nd Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 3rd Author's Name | Kenji Hatano |
| 3rd Author's Affiliation | Doshisha University(Doshisha Univ.) |
| Date | 2023-03-18 |
| Paper # | NLC2022-26 |
| Volume (vol) | vol.122 |
| Number (no) | NLC-449 |
| Page | pp.pp.38-43(NLC), |
| #Pages | 6 |
| Date of Issue | 2023-03-11 (NLC) |