题名 | An Effective Length Controlling Unit For Text Summarization |
作者 | |
发表日期 | 2021 |
会议名称 | The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) |
会议录名称 | Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
![]() |
ISBN | 9781954085541 |
页码 | 363-370 |
会议日期 | August 1-6, 2021 |
会议地点 | Bangkok, Thailand |
摘要 | Fixed length summarization aims at generating summaries with a preset number of words or characters. Most recent researches incorporate length information with word embeddings as the input to the recurrent decoding unit, causing a compromise between length controllability and summary quality. In this work, we present an effective length controlling unit Length Attention (LenAtten) to break this trade-off. Experimental results show that LenAtten not only brings improvements in length controllability and ROGUE scores but also has great generalization ability. In the task of generating a summary with the target length, our model is 732 times better than the bestperforming length controllable summarizer in length controllability on the CNN/Daily Mail dataset. |
DOI | 10.18653/v1/2021.findings-acl.31 |
URL | 查看来源 |
语种 | 英语English |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | https://repository.uic.edu.cn/handle/39GCC9TT/6862 |
专题 | 理工科技学院 |
通讯作者 | Su, Weifeng |
作者单位 | 1.Computer Science and Technology Programme, Division of Science and Technology, BNU-HKBU United International College, Zhuhai, China 2.Data Science Programme, Division of Science and Technology, BNU-HKBU United International College, Zhuhai, China 3.Guangdong Key Lab of AI and Multi-Modal Data Processing, BNU-HKBU United International College, Zhuhai, China |
第一作者单位 | 北师香港浸会大学 |
通讯作者单位 | 北师香港浸会大学 |
推荐引用方式 GB/T 7714 | Yu, Zhongyi,Wu, Zhenghao,Zheng, Haoet al. An Effective Length Controlling Unit For Text Summarization[C], 2021: 363-370. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论