A Hybrid Optimization Framework Fusing Word- and Sentence-Level Information for Extractive Summarization

doi:10.13209/j.0479-8023.2017.148

Acta Scientiarum Naturalium Universitatis Pekinensis ›› 2018, Vol. 54 ›› Issue (2): 229-235.DOI: 10.13209/j.0479-8023.2017.148

A Hybrid Optimization Framework Fusing Word- and Sentence-Level Information for Extractive Summarization

LIN Xinyi^1,2, YAN Rui^1,†, ZHAO Dongyan¹

1. Institute of Computer Science and Technology, Peking University, Beijing 100080
2. School of Electronic Engineering and Computer Science, Peking University, Beijing 100871

Received:2017-06-09 Revised:2017-08-31 Online:2018-03-20 Published:2018-03-20
Contact: YAN Rui, E-mail: ruiyan(at)pku.edu.cn

融合词、句层级信息的抽取式摘要优化框架

林心宜^1,2, 严睿^1,†, 赵东岩¹

1. 北京大学计算机科学技术研究所, 北京 100080
2. 北京大学信息科学技术学院, 北京 100871

通讯作者: 严睿, E-mail: ruiyan(at)pku.edu.cn
基金资助:
国家自然科学基金(61672058)、国家高技术研究发展计划(2015AA015403)和CCF-腾讯科研基金资助

Abstract

Abstract:

In order to fuse word-level and sentence-level information from different semantic spaces, the authors propose a hybrid optimization framework to optimize word-level information while simultaneously incorporate sentence-level information as constraints. The optimization is conducted by iterative unit substitutions. The performance on DUC benchmark datasets demonstrates the effectiveness of proposed framework in terms of ROUGE evaluation.

Key words: extractive summarization, word-level information, sentence-level information, hybrid optimization framework

摘要：

提出一个混合的抽取式摘要优化框架, 在优化单词层级信息的同时, 将句子层级信息作为优化约束。在约束条件下, 该优化框架迭代地进行摘要文本中单元的替换, 得到不断逼近目标函数的最优解。与传统方法对比, 该框架在DUC数据集上获得ROUGE评测的高分, 证明了该框架的有效性。

关键词: 抽取式摘要生成, 词层级信息, 句层级信息, 混合迭代优化框架

CLC Number:

TP391

LIN Xinyi, YAN Rui, ZHAO Dongyan. A Hybrid Optimization Framework Fusing Word- and Sentence-Level Information for Extractive Summarization[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(2): 229-235.

林心宜, 严睿, 赵东岩. 融合词、句层级信息的抽取式摘要优化框架[J]. 北京大学学报（自然科学版）, 2018, 54(2): 229-235.

Add to citation manager EndNote|Ris|BibTeX

URL: https://xbna.pku.edu.cn/EN/10.13209/j.0479-8023.2017.148

https://xbna.pku.edu.cn/EN/Y2018/V54/I2/229

[1]	LIU Qiuhui, ZHANG Kunli, XU Hongfei, YU Shiwen, ZAN Hongying. Research on Automatic Recognition of Auxiliary “DE” [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(3): 466-474.
[2]	KE Yonghong, ZHU Yongfu, SUI Zhifang, YU Shiwen. A Method for Semantic Roles Labeling Consistency Calculation Based on Multi-features [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(3): 475-480.
[3]	YANG Meng, LI Peifeng, ZHU Qiaoming. An Approach of Sentence Similarity on Tree-LSTM [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(3): 481-486.
[4]	ZHANG Yu, ZENG Li, ZOU Lei. Regular Path Queries on Large Graph Data [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(2): 236-242.
[5]	WEI Xing, WANG Wei, CHEN Jingping, XIE Yanlu, ZHANG Jinsong. A Study of Articulatory Features Based Detection of Mandrain Pronunciation Erroneous Tendency for Automatic Annotation [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(2): 243-248.
[6]	ZHOU Nan, ZHAO Yue, LI Yaoqiang, XU Xiaona, CAIWANG Lamu, WU Licheng. Study on Continuous Speech Recognition Based on Bottleneck Features for Lhasa-Tibetan Dialect [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(2): 249-254.
[7]	TAN Yiming, WANG Mingwen, LI Maoxi. Neural Post-Editing Based on Machine Translation Quality Estimation [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(2): 255-261.
[8]	WU Huanqin, ZHANG Hongyang, LI Jingmei, ZHU Junguo, YANG Muyun, LI Sheng. Training Machine Translation Quality Estimation Model Based on Pseudo Data [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(2): 279-285.
[9]	Lü Shuning, DONG Zhian. Domain Term Extraction Using URL-Key [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(2): 262-270.
[10]	WANG Wenchao, Lü Xueqiang, ZHANG Kai, ZHOU Jianshe. Research on Automatic Writing of Football Game News [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(2): 271-278.
[11]	Wenhao YING, Xinyan XIAO, Sujian LI, Yajuan LÜ, Zhifang SUI. Improving Query-Focused Summarization with CNN-Based Similarity [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2017, 53(2): 197-203.
[12]	Qingsheng LI, Qiang XU, Jianguo XIAO, Quan LIU, Jiefang ZHANG. A Structure and Style Model for Chinese Character Dynamic Generation [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2017, 53(2): 219-229.
[13]	Yujing CHEN, Xueqiang LÜ, Jianshe ZHOU, Ning LI. Research on Automatic Writing of NBA Sports News [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2017, 53(2): 211-218.
[14]	Lilin ZHANG, Maoxi LI, Wenyan XIAO, Jianyi WAN, Mingwen WANG. Improve Automatic Evaluation of Machine Translation Using Specific-Domain Paraphrase [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2017, 53(2): 230-238.
[15]	Li DONG, Zhongqing WANG, Deyi XIONG. Stock Index Prediction Based on Text Information [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2017, 53(2): 273-278.

A Hybrid Optimization Framework Fusing Word- and Sentence-Level Information for Extractive Summarization

融合词、句层级信息的抽取式摘要优化框架

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics