Tags

Type your tag names separated by a space and hit enter

Multiview Convolutional Neural Networks for Multidocument Extractive Summarization.
IEEE Trans Cybern. 2017 Oct; 47(10):3230-3242.IT

Abstract

Multidocument summarization has gained popularity in many real world applications because vital information can be extracted within a short time. Extractive summarization aims to generate a summary of a document or a set of documents by ranking sentences and the ranking results rely heavily on the quality of sentence features. However, almost all previous algorithms require hand-crafted features for sentence representation. In this paper, we leverage on word embedding to represent sentences so as to avoid the intensive labor in feature engineering. An enhanced convolutional neural networks (CNNs) termed multiview CNNs is successfully developed to obtain the features of sentences and rank sentences jointly. Multiview learning is incorporated into the model to greatly enhance the learning capability of original CNN. We evaluate the generic summarization performance of our proposed method on five Document Understanding Conference datasets. The proposed system outperforms the state-of-the-art approaches and the improvement is statistically significant shown by paired t -test.

Links

Publisher Full Text (DOI)

Authors

Zhang Y
No affiliation info available
Er MJ
No affiliation info available
Zhao R
No affiliation info available
Pratama M
No affiliation info available

MeSH

AlgorithmsData MiningMachine LearningNatural Language ProcessingNeural Networks, Computer

Pub Type(s)

Journal Article

Language

eng

PubMed ID

27913371

Citation

Zhang, Yong, et al. "Multiview Convolutional Neural Networks for Multidocument Extractive Summarization." IEEE Transactions On Cybernetics, vol. 47, no. 10, 2017, pp. 3230-3242.
Zhang Y, Er MJ, Zhao R, et al. Multiview Convolutional Neural Networks for Multidocument Extractive Summarization. IEEE Trans Cybern. 2017;47(10):3230-3242.
Zhang, Y., Er, M. J., Zhao, R., & Pratama, M. (2017). Multiview Convolutional Neural Networks for Multidocument Extractive Summarization. IEEE Transactions On Cybernetics, 47(10), 3230-3242. https://doi.org/10.1109/TCYB.2016.2628402
Zhang Y, et al. Multiview Convolutional Neural Networks for Multidocument Extractive Summarization. IEEE Trans Cybern. 2017;47(10):3230-3242. PubMed PMID: 27913371.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Multiview Convolutional Neural Networks for Multidocument Extractive Summarization. AU - Zhang,Yong, AU - Er,Meng Joo, AU - Zhao,Rui, AU - Pratama,Mahardhika, Y1 - 2016/11/28/ PY - 2016/12/4/pubmed PY - 2018/7/24/medline PY - 2016/12/4/entrez SP - 3230 EP - 3242 JF - IEEE transactions on cybernetics JO - IEEE Trans Cybern VL - 47 IS - 10 N2 - Multidocument summarization has gained popularity in many real world applications because vital information can be extracted within a short time. Extractive summarization aims to generate a summary of a document or a set of documents by ranking sentences and the ranking results rely heavily on the quality of sentence features. However, almost all previous algorithms require hand-crafted features for sentence representation. In this paper, we leverage on word embedding to represent sentences so as to avoid the intensive labor in feature engineering. An enhanced convolutional neural networks (CNNs) termed multiview CNNs is successfully developed to obtain the features of sentences and rank sentences jointly. Multiview learning is incorporated into the model to greatly enhance the learning capability of original CNN. We evaluate the generic summarization performance of our proposed method on five Document Understanding Conference datasets. The proposed system outperforms the state-of-the-art approaches and the improvement is statistically significant shown by paired t -test. SN - 2168-2275 UR - https://www.unboundmedicine.com/medline/citation/27913371/Multiview_Convolutional_Neural_Networks_for_Multidocument_Extractive_Summarization_ DB - PRIME DP - Unbound Medicine ER -