WEKO3
アイテム
Automatic Few-shot Selection on In-Context Learning for Aspect Term Extraction
http://hdl.handle.net/10228/0002001156
http://hdl.handle.net/10228/000200115687c5e303-2c9d-4151-b8ba-bf131f7e720d
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
10443064.pdf (438 KB)
|
|
| アイテムタイプ | 共通アイテムタイプ(1) | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2025-01-24 | |||||||||||
| タイトル | ||||||||||||
| タイトル | Automatic Few-shot Selection on In-Context Learning for Aspect Term Extraction | |||||||||||
| 言語 | en | |||||||||||
| 著者 |
Imazato, Koki
× Imazato, Koki
× 嶋田, 和孝
WEKO
13734
|
|||||||||||
| 著作権関連情報 | ||||||||||||
| 権利情報 | Copyright (c) 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |||||||||||
| 抄録 | ||||||||||||
| 内容記述タイプ | Abstract | |||||||||||
| 内容記述 | In this paper, we handle aspect term extraction with In-Context Learning (ICL) as the target task. ICL is a method for learning Large Language Models. Instead of updating the model's parameters, prompts are provided to guide it to perform a target task. While the strength of ICL is that the model does not need to undergo additional training, the prompt includes input-output instances that cause instability in accuracy. The instances are called few-shot. Hence, selecting appropriate instances has the most important role in ICL. For this purpose, we propose a selection method with active learning. Active learning is a method of selecting instances that are useful to the model for training from unlabeled data. We regard the active learning-based approach as a sub-task for the target task. We introduce two types of sub-tasks and evaluate the effectiveness of them in the target task. | |||||||||||
| 言語 | en | |||||||||||
| 備考 | ||||||||||||
| 内容記述タイプ | Other | |||||||||||
| 内容記述 | 18th International Conference on E-Service and Knowledge Management (ESKM 2024), July 6 - 12, 2024, Takamatsu, Japan | |||||||||||
| 言語 | en | |||||||||||
| 書誌情報 |
en : 2024 16th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) p. 15-20, 発行日 2024-10-15 |
|||||||||||
| 出版社 | ||||||||||||
| 出版者 | IEEE | |||||||||||
| キーワード | ||||||||||||
| 主題Scheme | Other | |||||||||||
| 主題 | Aspect term extraction | |||||||||||
| キーワード | ||||||||||||
| 主題Scheme | Other | |||||||||||
| 主題 | In-context learning | |||||||||||
| キーワード | ||||||||||||
| 主題Scheme | Other | |||||||||||
| 主題 | Few-shot learning | |||||||||||
| キーワード | ||||||||||||
| 主題Scheme | Other | |||||||||||
| 主題 | Active learning | |||||||||||
| キーワード | ||||||||||||
| 主題Scheme | Other | |||||||||||
| 主題 | GPT-4 | |||||||||||
| 言語 | ||||||||||||
| 言語 | eng | |||||||||||
| 資源タイプ | ||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||
| 資源タイプ | journal article | |||||||||||
| 出版タイプ | ||||||||||||
| 出版タイプ | AM | |||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa | |||||||||||
| DOI | ||||||||||||
| 識別子タイプ | DOI | |||||||||||
| 関連識別子 | https://doi.org/10.1109/IIAI-AAI63651.2024.00012 | |||||||||||
| ISBN | ||||||||||||
| 識別子タイプ | ISBN | |||||||||||
| 関連識別子 | 979-8-3503-7790-3 | |||||||||||
| 会議記述 | ||||||||||||
| 会議名 | International Conference on E-Service and Knowledge Management | |||||||||||
| 言語 | en | |||||||||||
| 回次 | 18 | |||||||||||
| 開始年 | 2024 | |||||||||||
| 開始月 | 07 | |||||||||||
| 開始日 | 06 | |||||||||||
| 終了年 | 2024 | |||||||||||
| 終了月 | 07 | |||||||||||
| 終了日 | 12 | |||||||||||
| 開催国 | JPN | |||||||||||
| 査読の有無 | ||||||||||||
| 値 | yes | |||||||||||
| 研究者情報 | ||||||||||||
| URL | https://hyokadb02.jimu.kyutech.ac.jp/html/196_ja.html | |||||||||||
| 論文ID（連携） | ||||||||||||
| 値 | 10443064 | |||||||||||
| 連携ID | ||||||||||||
| 値 | 12444 | |||||||||||
