题名 | A Scoring Model Assisted by Frequency for Multi-Document Summarization |
作者 | |
发表日期 | 2021 |
会议名称 | Artificial Neural Networks and Machine Learning – ICANN 2021 |
会议录名称 | Artificial Neural Networks and Machine Learning – ICANN 2021: 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 14–17, 2021, Proceedings, Part V
![]() |
会议录编者 | Igor Farkaš, Paolo Masulli, Sebastian Otte, Stefan Wermter |
ISBN | 9783030863821 |
ISSN | 0302-9743 |
卷号 | Lecture Notes in Computer Science (LNCS, volume 12895) |
页码 | 309-320 |
会议日期 | September 14–17, 2021 |
会议地点 | Bratislava, Slovakia |
出版地 | Cham |
出版者 | Springer |
摘要 | While position information plays a significant role in sentence scoring of single document summarization, the repetition of content among different documents greatly impacts the salience scores of sentences in multi-document summarization. Introducing frequencies information can help identify important sentences which are generally ignored when only considering position information before. Therefore, in this paper, we propose a scoring model, SAFA (Self-Attention with Frequency Graph) which combines position information with frequency to identify the salience of sentences. The SAFA model constructs a frequency graph at the multi-document level based on the repetition of content of sentences, and assigns initial score values to each sentence based on the graph. The model then uses the position-aware gold scores to train a self-attention mechanism, obtaining the sentence significance at its single document level. The score of each sentence is updated by combing position and frequency information together. We train and test the SAFA model on the large-scale multi-document dataset Multi-News. The extensive experimental results show that the model incorporating frequency information in sentence scoring outperforms the other state-of-the-art extractive models. |
关键词 | Frequency Graph Multiple document summarization Position information |
DOI | 10.1007/978-3-030-86383-8_25 |
URL | 查看来源 |
语种 | 英语English |
Scopus入藏号 | 2-s2.0-85115672057 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | https://repository.uic.edu.cn/handle/39GCC9TT/6046 |
专题 | 理工科技学院 |
作者单位 | 1.Computer Science and Technology Programme,Division of Science and Technology,BNU-HKBU United International College,Guangdong,China 2.Department of Computer Science,Hong Kong Baptist University,Hong Kong,China |
第一作者单位 | 北师香港浸会大学 |
推荐引用方式 GB/T 7714 | Yu, Yue,Wu, Mutong,Su, Weifenget al. A Scoring Model Assisted by Frequency for Multi-Document Summarization[C]//Igor Farkaš, Paolo Masulli, Sebastian Otte, Stefan Wermter. Cham: Springer, 2021: 309-320. |
条目包含的文件 | 条目无相关文件。 |
个性服务 |
查看访问统计 |
谷歌学术 |
谷歌学术中相似的文章 |
[Yu, Yue]的文章 |
[Wu, Mutong]的文章 |
[Su, Weifeng]的文章 |
百度学术 |
百度学术中相似的文章 |
[Yu, Yue]的文章 |
[Wu, Mutong]的文章 |
[Su, Weifeng]的文章 |
必应学术 |
必应学术中相似的文章 |
[Yu, Yue]的文章 |
[Wu, Mutong]的文章 |
[Su, Weifeng]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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