Extractive Summarization of Documents by Combining Semantic Content and Non-Structured Features
作者： Shan Yang , Yating Yang , Chenggang Mi , Yirong Pan , Lei Wang
DOI: 10.1109/IALP.2018.8629170
关键词:
摘要: Current extractive summarization models utilize semantic content and non-structured features of sentences respectively to identify the sentence importance. In this paper, we present a new approach by combining based on convolutional neural network recurrent network, called CRSum. model, firstly, are learned network. Secondly, investigate whether can be used as summary according above knowledge learned. What's more, all predictions CRSum model interpreted visualizing sentences. Experimental results LSCTC CNN/Daily Mail corpus show that its performance is better than baseline systems surpass state-of-the-art in Rouge-L.
sci-hub.se 参考文章(19)
Ilya Sutskever, Geoffrey E. Hinton, Alex Krizhevsky, Ruslan R. Salakhutdinov, Nitish Srivastava, Improving neural networks by preventing co-adaptation of feature detectors arXiv: Neural and Evolutionary Computing. ,(2012)
Çaglar Gülçehre, Yoshua Bengio, Yoshua Bengio, Yoshua Bengio, KyungHyun Cho, Junyoung Chung, Empirical evaluation of gated recurrent neural networks on sequence modeling arXiv: Neural and Evolutionary Computing. ,(2014)
H. P. Luhn, The automatic creation of literature abstracts Ibm Journal of Research and Development. ,vol. 2, pp. 159- 165 ,(1958) , 10.1147/RD.22.0159
Wesley T. Chuang, Jihoon Yang, Extracting sentence segments for text summarization: a machine learning approach international acm sigir conference on research and development in information retrieval. pp. 152- 159 ,(2000) , 10.1145/345508.345566
Julian Kupiec, Jan Pedersen, Francine Chen, A trainable document summarizer Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '95. pp. 68- 73 ,(1995) , 10.1145/215206.215333
Krysta Svore, Lucy Vanderwende, Christopher Burges, Enhancing Single-Document Summarization by Combining RankNet and Third-Party Sources empirical methods in natural language processing. pp. 448- 457 ,(2007)
Ani Nenkova, Lucy Vanderwende, Kathleen McKeown, A compositional context sensitive multi-document summarizer Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '06. pp. 573- 580 ,(2006) , 10.1145/1148170.1148269
Ronald Brandow, Karl Mitze, Lisa F. Rau, Automatic condensation of electronic publications by sentence selection Information Processing and Management. ,vol. 31, pp. 675- 685 ,(1995) , 10.1016/0306-4573(95)00052-I
Yann Lecun, Jean Ponce, Jean Ponce, Y-lan Boureau, Y-lan Boureau, A Theoretical Analysis of Feature Pooling in Visual Recognition international conference on machine learning. pp. 111- 118 ,(2010)
K. Kaikhah, Automatic text summarization with neural networks Information Systems. ,vol. 1, pp. 40- 44 ,(2004) , 10.1109/IS.2004.1344634