Skip to main content
SpringerLink
Log in

CRHASum: extractive text summarization with contextualized-representation hierarchical-attention summarization network

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The requirements for automatic document summarization that can be applied to practical applications are increasing rapidly. As a general sentence regression architecture, extractive text summarization captures sentences from a document by leveraging externally related information. However, existing sentence regression approaches have not employed features that mine the contextual information and relations among sentences. To alleviate this problem, we present a neural network model, namely the Contextualized-Representation Hierarchical-Attention Summarization (CRHASum), that uses the contextual information and relations among sentences to improve the sentence regression performance for extractive text summarization. This framework makes the most of their advantages. One advantage is that the contextual representation is allowed to vary across linguistic context information, and the other advantage is that the hierarchical attention mechanism is able to capture the contextual relations from the word-level and sentence-level by using the Bi-GRU. With this design, the CRHASum model is capable of paying attention to the important context in the surrounding context of a given sentence for extractive text summarization. We carry out extensive experiments on three benchmark datasets. CRHASum alone can achieve comparable performance to the state-of-the-art approach. Meanwhile, our method significantly outperforms the state-of-the-art baselines in terms of multiple ROUNG metrics and includes a few basic useful features.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Notes

  1. http://duc.nist.gov/.

  2. ROUGE-1.5.5 with options: −n 2 –m –u –c 95 –x –r 1000 –f A –p 0.5 –t 0.

  3. http://stanfordnlp.github.io/CoreNLP/.

References

  1. Chopra S, Auli M, Rush AM (2016) Abstractive sentence summarization with attentive recurrent neural networks. In: Proceedings of the 2016 conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 93–98

  2. Takase S, Suzuki J, Okazaki N et al (2016) Neural headline generation on abstract meaning representation. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp 1054–1059

  3. Cao Z, Wei F, Li S, Li W, Zhou M, Wang H (2015) Learning summary prior representation for extractive summarization. In: ACL

  4. Wan X, Cao Z, Wei F, Li S, Zhou M (2015) Multi-document summarization via discriminative summary reranking. CoRR

  5. Feng C, Cai F, Chen H et al (2018) Attentive encoder-based extractive text summarization. In: Proceedings of the 27th ACM International conference on information and knowledge management. ACM, pp 1499–1502

  6. Ren P, Chen Z, Ren Z et al (2017) Leveraging contextual sentence relations for extractive summarization using a neural attention model. In: Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval. ACM, pp 95–104

  7. Ren P, Wei F, Chen Z, Ma J, Zhou M (2016) A redundancy-aware sentence regression framework for extractive summarization. In: COLING

  8. Wan X, Zhang J (2014) CTSUM: extracting more certain summaries for news articles. In: SIGIR

  9. Isonuma M, Fujino T, Mori J et al (2017) Extractive summarization using multi-task learning with document classification. In: Proceedings of the 2017 Conference on empirical methods in natural language processing, pp 2101–2110

  10. Radev DR, Jing H, Budzikowska M (2000) Centroid-based summarization of multiple documents: sentence extraction, utility-based evaluation, and user studies. In: NAACL-ANLP

  11. Mihalcea R (2004) Graph-based ranking algorithms for sentence extraction, applied to text summarization. In: ACL

  12. Mihalcea R, Tarau P (2004) TextRank: bringing order into texts. In: EMNLP

  13. Erkan G, Radev DR (2004) LexRank: graph-based lexical centrality as salience in text summarization. JAIR 22(1):457–479

    Article  Google Scholar 

  14. Wan X, Yang J (2008) Multi-document summarization using cluster-based link analysis. In: SIGIR

  15. Goldstein J, Mittal V, Carbonell J, Kantrowitz M (2000) Multi-document summarization by sentence extraction. In: NAACL-ANLP

  16. Lin H, Bilmes J (2011) A class of submodular functions for document summarization. In: NAACL-HLT

  17. Kupiec J, Pedersen J, Chen F (1995) A trainable document summarizer. In: SIGIR

  18. Li S, Ouyang Y, Wang W, Sun B (2007) Multi-document summarization using support vector regression. In: DUC

  19. Hu Y, Wan X (2015) PPSGen: learning-based presentation slides generation for academic papers. TKDE 27(4):1085–1097

    Google Scholar 

  20. Gillick D, Favre B (2009) A scalable global model for summarization. In: ILP-NLP

  21. Kobayashi H, Noguchi M, Yatsuka T (2015) Summarization based on embedding distributions. In: EMNLP

  22. Yin W, Pei Y (2015) Optimizing sentence modeling and selection for document summarization. In: IJCAI

  23. Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. Comput Sci

  24. Shen T, Zhou T, Long G et al (2018) Disan: directional self-attention network for rnn/cnn-free language understanding. In: AAAI

  25. Du J, Xu R, He Y et al (2017) Stance classification with target-specific neural attention. In: Twenty-sixth international joint conference on artificial intelligence, pp 3988–3994

  26. Gui L, Hu J, He Y et al (2017) A question answering approach to emotion cause extraction. arXiv:1708.05482

  27. Lu J, Yang J, Batra D et al (2016) Hierarchical question-image co-attention for visual question answering. In: Advances in neural information processing systems, pp 289–297

  28. Kim J, Kong D, Lee JH (2018) Self-attention-based message-relevant response generation for neural conversation model. arXiv:1805.08983

  29. Fan A, Lewis M, Dauphin Y (2018) Hierarchical neural story generation. arXiv:1805.04833

  30. Mikolov T, Chen K, Corrado G et al (2013) Efficient estimation of word representations in vector space. In: Proceedings of ICLR:1301.3781

  31. Pennington J, Socher R, Manning C (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532–1543

  32. Peters ME, Neumann M, Iyyer M et al (2018) Deep contextualized word representations

  33. Chung J, Gulcehre C, Cho KH et al (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555

  34. Zhang H, Li J, Ji Y et al (2017) Understanding subtitles by character-level sequence-to-sequence learning. IEEE Trans Ind Inf 13(2):616–624

    Article  Google Scholar 

  35. Zhang H, Wang S, Mingbo Z et al (2018) Locality reconstruction models for book representation. IEEE Trans Knowl Data Eng 99:1

    Google Scholar 

  36. Rankel PA, Conroy JM, Dang HT, Nenkova A (2013) A decade of automatic content evaluation of news summaries: reassessing the state of the art. In: ACL

  37. Lin C-Y (2004) Rouge: a package for automatic evaluation of summaries. In: ACL

  38. Owczarzak K, Conroy JM, Dang HT, Nenkova A (2012) An assessment of the accuracy of automatic evaluation in summarization. In: NAACL-HLT

  39. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overing. JMLR 15(1):1929–1958

    MATH  Google Scholar 

  40. Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. JMLR 12:2121–2159

    MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

This work is partially supported by grant from the Natural Science Foundation of China (Nos. 61632011, 61572102, 61702080, 61602079, 61806038), the Ministry of Education Humanities and Social Science Project (No. 16YJCZH12), the Fundamental Research Funds for the Central Universities (DUT18ZD102, DUT19RC(4)016), the National Key Research Development Program of China (No. 2018YFC0832101) and China Postdoctoral Science Foundation (No. 2018M631788).

Author information

Authors and Affiliations

  1. Department of Computer Science and Technology, Dalian University of Technology, Dalian, China

    Yufeng Diao, Hongfei Lin, Liang Yang, Xiaochao Fan, Yonghe Chu, Di Wu & Kan Xu

  2. School of Computer Science and Technology, Inner Mongolia University for Nationalities, Tongliao, China

    Yufeng Diao

  3. Xinjiang Normal University, Xinjiang, China

    Xiaochao Fan

  4. School of Software, Dalian University of Technology, Dalian, Liaoning, China

    Dongyu Zhang

Authors
  1. Yufeng Diao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hongfei Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Liang Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xiaochao Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yonghe Chu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Di Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Dongyu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Kan Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hongfei Lin.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Human and animal rights

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Diao, Y., Lin, H., Yang, L. et al. CRHASum: extractive text summarization with contextualized-representation hierarchical-attention summarization network. Neural Comput & Applic 32, 11491–11503 (2020). https://doi.org/10.1007/s00521-019-04638-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-019-04638-3

Keywords

Search

Navigation