Knowledge Commons of Institute of Automation,CAS
Augmenting Neural Sentence Summarization through Extractive Summarization | |
Zhu, Junnan1; Zhou, Long1; Li, Haoran1; Zhang, Jiajun1; Zhou, Yu1; Zong, Chengqing1,2 | |
2017-11 | |
会议名称 | Proceedings of the 6th Conference on Natural Language Processing and Chinese Computing |
会议日期 | 2017.11.8-2017.11.12 |
会议地点 | Dalian, China |
会议录编者/会议主办者 | CCF |
出版者 | Springer |
摘要 | Neural sequence-to-sequence model has achieved great success in abstractive summarization task. However, due to the limit of input length, most of previous works can only utilize lead sentences as the input to generate the abstractive summarization, which ignores crucial information of the document. To alleviate this problem, we propose a novel approach to improve neural sentence summarization by using extractive summarization, which aims at taking full advantage of the document information as much as possible. Furthermore, we present both of streamline strategy and system combination strategy to achieve the fusion of the contents in di erent views, which can be easily adapted to other domains. Experimental results on CNN/Daily Mail dataset demonstrate both our proposed strategies can signi cantly improve the performance of neural sentence summarization. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39086 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
作者单位 | 1.University of Chinese Academy of Sciences National Laboratory of Pattern Recognition, CASIA 2.CAS Center for Excellence in Brain Science and Intelligence Technology |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhu, Junnan,Zhou, Long,Li, Haoran,et al. Augmenting Neural Sentence Summarization through Extractive Summarization[C]//CCF:Springer,2017. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
NLPCC.pdf(413KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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