Improving Query-Focused Summarization with CNN-Based Similarity

被引：0
|
作者：
Ying W. [1 ]
Xiao X. [2 ]
Li S. [1 ]
Lü Y. [2 ]
Sui Z. [1 ]
机构：
[1] School of Electronic Engineering and Computer Science, Peking University, Beijing
[2] Baidu Inc., Beijing
来源：
Li, Sujian (lisujian@pku.edu.cn) | 1600年 / Peking University卷 / 53期
关键词：
Convolutional neural; Max-margin learning; network; Query-focused summarization; Semantic similarity;
D O I：
10.13209/j.0479-8023.2017.028
中图分类号：
学科分类号：
摘要：
In search services, users can get information more conveniently by reading the succinct answers to their questions. This paper introduces a feature-based method for the query-focused summarization to extract the answer summary of a user query. A convolutional neural network (CNN) is used to learn the semantic representation of a sentence, by which the similarity between a candidate answer sentence and a user query is evaluated. The neural network is trained under the framework of max-margin learning. Experiments in Baidu Knows verify that the proposed method can generate the concise answer of a user query. © 2017 Peking University.
引用
收藏
页码：197 / 203
页数：6
相关论文
共 15 条
  • [1] Cao Z., Wei F., Li S., Et al., Learning summary prior representation for extractive summarization, Proceedings of ACL-2015, pp. 829-833, (2015)
  • [2] Cao Z., Wei F., Dong L., Et al., Ranking with recursive neural networks and its application to multi-document summarization, Proceedings of AAAI-2015, pp. 2153-2159, (2015)
  • [3] Ouyang Y., Li W., Li S., Et al., Applying regression models to query-focused multi-document summarization, Information Processing & Management, 47, 2, pp. 227-237, (2011)
  • [4] Svore K.M., Vanderwende L., Burges A.C., Enhancing single-document summarization by combining ranknet and third-party sources, Proceedings of EMNLP-2007, pp. 448-457, (2007)
  • [5] Ye S., Qiu L., Chua T.S., Et al., NUS at DUC 2005: understanding documents via concept links, Proceedings of the Fifth Document Understanding Conference, pp. 1-6, (2005)
  • [6] Li S., Ouyang Y., Wang W., Et al., Multi-document summarization using support vector regression, Proceedings of the 7th Document Understanding Conference, pp. 1-5, (2007)
  • [7] Kim Y., Convolutional neural networks for sentence classification, Proceedings of EMNLP-2014, pp. 1746-1751, (2014)
  • [8] Kalchbrenner N., Grefenstette E., Blunsom P., A con-volutional neural network for modelling sentences, Proceedings of ACL-2014, pp. 655-665, (2014)
  • [9] He H., Gimpel K., Lin J., Multi-perspective sentence similarity modeling with convolutional zeural net-works, Proceedings of EMNLP-2015, pp. 1576-1586, (2015)
  • [10] Herbrich R., Graepel T., Obermayer K., Support vector learning for ordinal regression, Proceedings of the 9th International Conference on Aritifical Neural Networks (ICANN), pp. 97-102, (1999)
12