WEKO3
アイテム
Content Order-Controllable MR-to-Text
http://hdl.handle.net/10061/0002000115
http://hdl.handle.net/10061/000200011581c5ee6d-36c4-4961-b05d-dc6aac9dbe9d
| アイテムタイプ | 学術雑誌論文 / Journal Article(1) | |||||||
|---|---|---|---|---|---|---|---|---|
| 公開日 | 2024-01-30 | |||||||
| タイトル | ||||||||
| タイトル | Content Order-Controllable MR-to-Text | |||||||
| 言語 | ||||||||
| 言語 | eng | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | Controllable text generation | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | data augmentation | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | data-to-text | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | meaning representation | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | natural language generation | |||||||
| 資源タイプ | ||||||||
| 資源タイプ | journal article | |||||||
| アクセス権 | ||||||||
| アクセス権 | open access | |||||||
| 著者 |
Toyama, Keisuke
× Toyama, Keisuke
× 須藤, 克仁× 中村, 哲 |
|||||||
| 抄録 | ||||||||
| 内容記述タイプ | Abstract | |||||||
| 内容記述 | Content order is critical in natural language generation (NLG) for emphasizing the focus of a generated text passage. In this paper, we propose a novel MR (meaning representation)-to-text method that controls the order of the MR values in a generated text passage based on the given order constraints. We use an MR-text dataset with additional value order annotations to train our order-controllable MR-to-text model. We also use it to train a text-to-MR model to check whether the generated text passage correctly reflects the original MR. Furthermore, we augment the dataset with synthetic MR-text pairs to mitigate the discrepancy in the number of non-empty attributes between the training and test conditions and use it to train another order-controllable MR-to-text model. Our proposed methods demonstrate better NLG performance than the baseline methods without order constraints in automatic and subjective evaluations. In particular, the augmented dataset effectively reduces the number of deletion, insertion, and substitution errors in the generated text passages. | |||||||
| 書誌情報 |
en : IEEE Access 巻 11, p. 129353-129365, 発行日 2023-11-16 |
|||||||
| 出版者 | ||||||||
| 出版者 | IEEE | |||||||
| ISSN | ||||||||
| 収録物識別子タイプ | EISSN | |||||||
| 収録物識別子 | 2169-3536 | |||||||
| 出版者版DOI | ||||||||
| 関連タイプ | isReplacedBy | |||||||
| 識別子タイプ | DOI | |||||||
| 関連識別子 | https://doi.org/10.1109/ACCESS.2023.3334139 | |||||||
| 出版者版URI | ||||||||
| 関連タイプ | isReplacedBy | |||||||
| 識別子タイプ | URI | |||||||
| 関連識別子 | https://ieeexplore.ieee.org/document/10320352 | |||||||
| 権利 | ||||||||
| 権利情報Resource | https://creativecommons.org/licenses/by-nc-nd/4.0/ | |||||||
| 権利情報 | c 2023 The Authors. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ | |||||||
| 著者版フラグ | ||||||||
| 出版タイプ | NA | |||||||
