WEKO3
アイテム
Abstractive Document Summarization with Summary-length Prediction
http://hdl.handle.net/10061/0002000460
http://hdl.handle.net/10061/00020004602009a0eb-c0a3-41e9-9a95-09ed00f22f5d
| アイテムタイプ | 会議発表論文 / Conference Paper(1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2024-06-07 | |||||||||
| タイトル | ||||||||||
| タイトル | Abstractive Document Summarization with Summary-length Prediction | |||||||||
| 言語 | ||||||||||
| 言語 | eng | |||||||||
| 資源タイプ | ||||||||||
| 資源タイプ | conference paper | |||||||||
| アクセス権 | ||||||||||
| アクセス権 | open access | |||||||||
| 著者 |
Kwon, Jingun
× Kwon, Jingun
× 上垣外, 英剛× Okumura, Manabu
|
|||||||||
| 抄録 | ||||||||||
| 内容記述タイプ | Abstract | |||||||||
| 内容記述 | Recently, we can obtain a practical abstractive document summarization model by fine-tuning a pre-trained language model (PLM). Since the pre-training for PLMs does not consider summarization-specific information such as the target summary length, there is a gap between the pre-training and fine-tuning for PLMs in summarization tasks. To fill the gap, we propose a method for enabling the model to understand the summarization-specific information by predicting the summary length in the encoder and generating a summary of the predicted length in the decoder in fine-tuning. Experimental results on the WikiHow, NYT, and CNN/DM datasets showed that our methods improve ROUGE scores from BART by generating summaries of appropriate lengths. Further, we observed about 3.0, 1,5, and 3.1 point improvements for ROUGE-1, -2, and -L, respectively, from GSum on the WikiHow dataset. Human evaluation results also showed that our methods improve the informativeness and conciseness of summaries. | |||||||||
| 書誌情報 |
en : Findings of the Association for Computational Linguistics: EACL 2023 p. 618-624, 発行日 2023-05-02 |
|||||||||
| 会議情報 | ||||||||||
| 会議名 | Findings of the Association for Computational Linguistics: EACL 2023 | |||||||||
| 開始年 | 2023 | |||||||||
| 開始月 | 05 | |||||||||
| 開始日 | 02 | |||||||||
| 終了年 | 2023 | |||||||||
| 終了月 | 05 | |||||||||
| 終了日 | 06 | |||||||||
| 開催地 | Dubrovnik | |||||||||
| 開催国 | HRV | |||||||||
| 出版者 | ||||||||||
| 出版者 | Association for Computational Linguistics | |||||||||
| 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/10.18653/v1/2023.findings-eacl.45 | |||||||||
| 出版者版URI | ||||||||||
| 関連タイプ | isReplacedBy | |||||||||
| 識別子タイプ | URI | |||||||||
| 関連識別子 | https://aclanthology.org/2023.findings-eacl.45/ | |||||||||
| 権利 | ||||||||||
| 権利情報Resource | http://creativecommons.org/licenses/by/4.0/ | |||||||||
| 権利情報 | $00A92023 Association for Computational Linguistics | |||||||||
| 著者版フラグ | ||||||||||
| 出版タイプ | NA | |||||||||
