Skip to main content

A Compare-Aggregate Model with External Knowledge for Query-Focused Summarization

  • 581 Accesses

Part of the Lecture Notes in Computer Science book series (LNISA,volume 12343)

Abstract

Query-focused extractive summarization aims to create a summary by selecting sentences from original document according to query relevance and redundancy. With recent advances of neural network models in natural language processing, attention mechanism is widely used to address text summarization task. However, existing methods are always based on a coarse-grained sentence-level attention, which likely to miss the intent of query and cause relatedness misalignment. To address the above problem, we introduce a fine-grained and interactive word-by-word attention to the query-focused extractive summarization system. In that way, we capture the real intent of query. We utilize a Compare-Aggregate model to implement the idea, and simulate the interactively attentive reading and thinking of human behavior. We also leverage external conceptual knowledge to enrich the model and fill the expression gap between query and document. In order to evaluate our method, we conduct experiments on DUC 2005–2007 query-focused summarization benchmark datasets. Experimental results demonstrate that our proposed approach achieves better performance than state-of-the-art.

Keywords

  • Query-focused summarization
  • Extractive summarization
  • Attention
  • External knowledge

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-62008-0_5
  • Chapter length: 16 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   89.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-62008-0
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   119.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.

Notes

  1. 1.

    https://github.com/commonsense/conceptnet5/wiki/API.

  2. 2.

    https://pypi.org/project/bert-embedding/.

References

  1. Dang, H.T.: Overview of Duc 2005. In: Proceedings of DUC, pp. 1–12 (2005)

    Google Scholar 

  2. Wenpeng, Y., Yulong, P.: Optimizing sentence modeling and selection for document summarization. In Proceedings of IJCAI, pp. 1383–1389 (2015)

    Google Scholar 

  3. Ziqiang, C., Furu, W., Sujian, L., Wenjie, L., Ming, Z., Houfeng, W.: Learning summary prior representation for extractive summarization. In: Proceedings of IJCAI, Short Paper, pp. 829–833 (2015)

    Google Scholar 

  4. Ziqiang, C., Wenjie, L., Sujian, L., Furu, W., Yanran, L.:. AttSum: joint learning of focusing and summarization with neural attention. In: Proceedings of COLING, pp. 547–556 (2016)

    Google Scholar 

  5. Preksha, N., Khapra, M.M., Anirban, L., Ravindran, B.: Diversity driven attention model for query-based abstractive summarization. In: Proceedings of ACL, pp. 1063–1072 (2017)

    Google Scholar 

  6. Shuohang, W., Jing, J.: A compare-aggregate model for matching text sequences. In: Proceedings of ICLR (2017)

    Google Scholar 

  7. Parikh Ankur, P., Oscar, T., Dipanjan, D., Jakob, U.: A decomposable attention model for natural language inference. In: Proceedings of EMNLP, pp. 2249–2255 (2016)

    Google Scholar 

  8. Weijie, B., Si, L., Zhao, Y., Guang, C., Zhiqing, L.: A compare-aggregate model with dynamic-clip attention for answer selection. In: Proceedings of CIKM, Short Paper, pages pp. 1987–1990 (2017)

    Google Scholar 

  9. Seunghyun, Y., Franck, D., Doo, K., Soon, B.T., Kyomin, J.: A compare-aggregate model with latent clustering for answer selection. In: Proceedings of CIKM, Short Paper, pp. 2093–2096 (2019)

    Google Scholar 

  10. Arbi, B., Xiaohua, L., Jian-Yun, N.: Integrating multiple resources for diversified query expansion. In: Proceedings of ECIR, pp. 437–442 (2014)

    Google Scholar 

  11. Sarasi, L., Sujan, P., Pavan, K., Amit, S.: Domain-specific hierarchical subgraph extraction: a recommendation use case. In: Proceedings of Big Data, pp. 666–675 (2017)

    Google Scholar 

  12. Sarasi, L., Sujan, P., Pavan, K., Amit, S.: Domain-specific hierarchical subgraph extraction: a recommendation use case. In: Proceedings of Big Data, pp. 666–675 (2017)

    Google Scholar 

  13. Qian, C., Xiaodan, Z., Zhen-Hua, L., Diana, I., Si, W.: Neural natural language inference models enhanced with external knowledge. In: Proceedings of ACL, pp. 2406–2417 (2018)

    Google Scholar 

  14. Robyn, S., Joshua, C., Catherine, H.: ConceptNet 5.5: an open multilingual graph of general knowledge. In: Proceedings of AAAI, pp. 4444–4451 (2017)

    Google Scholar 

  15. Jacob, D., Ming-Wei, C., Kenton, L., Kristina, T.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171–4186 (2019)

    Google Scholar 

  16. Ashish, V., et al.: Attention is all you need. In: Proceedings of NIPS, pp. 5998–6008 (2017)

    Google Scholar 

  17. Robyn, S., Joanna, L.-D.: ConceptNet at SemEval-2017 Task 2: extending word embeddings with multilingual relational knowledge. In: Proceedings of SemEval workshop at ACL 2017, pp. 85–89 (2017)

    Google Scholar 

  18. Yoon, K.: Convolutional neural networks for sentence classification. In: Proceedings of EMNLP, pp. 1746–1751 (2014)

    Google Scholar 

  19. Guy, F., Haggai, R., Odellia, B., David, K.: Unsupervised query-focused multi-document summarization using the cross entropy method. In: Proceedings of SIGIR, Short Paper, pp. 961–964 (2017)

    Google Scholar 

  20. Jaime, C., Jade, G.: The use of MMR, diversity-based reranking for reordering documents and producing summaries. In: Proceedings of SIGIR, Short Paper, pp. 335–336 (1998)

    Google Scholar 

  21. Xiaojun, W., Jianguo, X.: Graph-based multi-modality learning for topic-focused multi-document summarization. In: Proceedings of IJCAI, pp. 1586–1591 (2009)

    Google Scholar 

  22. Sheng-hua, Z., Yan, L., Bin, L., Jing, L.: Query-oriented unsupervised multi-document summarization via deeplearning model. Expert Syst. Appl. 42(21), 8146–8155 (2015)

    CrossRef  Google Scholar 

  23. Mittul, S., Arunav, M.: Long-span language models for query-focused unsupervised extractive text summarization. In: Proceedings of ECIR, pp. 657–664 (2018)

    Google Scholar 

  24. Michel, G.: A skip-chain conditional random field for ranking meeting utterances by importance. In: Proceedings of EMNLP, pp. 364–372 (2006)

    Google Scholar 

  25. You, O., Wenjie, L., Sujian, L., Qin, L.: Applying regression models to query-focused multidocument summarization. Inf. Process. Manage. 47(2), 227–237 (2011)

    CrossRef  Google Scholar 

  26. Chen, L., Xian, Q., Yang, L.: Using supervised bigram-based ILP for extractive summarization. In: Proceedings of ACL, pp. 1004–1013 (2013)

    Google Scholar 

  27. Chao, S., Tao,L.: Learning to rank for query-focused multi-document summarization. In: Proceedings of ICDM, pp. 626–634 (2011)

    Google Scholar 

  28. Jianpeng, C., Lapata, M.: Neural summarization by extracting sentences and words. In: Proceedings of ACL, pp. 484–494 (2016)

    Google Scholar 

  29. Pengjie, R., Zhumin, C.: Sentence relation for extractive summarization with deep neural network. TOIS 36(4), 1–32 (2018)

    Google Scholar 

  30. Kobayashi Hayato, M.N., Yatsuka, T.: Summarization based on embedding distributions. In: Proceedings of EMNLP, pp. 1984–1989 (2015)

    Google Scholar 

  31. Yanran, L., Li, S.: Query-focused multi-document summarization: combining a topic model with graph-based semi-supervised learning. In: Proceedings of COLING, pp. 1197–1207 (2014)

    Google Scholar 

  32. Tatsuya, I., Kazuya, M., Hayato, K., Hiroya, T., Manabu, O.: Distant supervision for extractive question summarization. In: Proceedings of ECIR, pp. 182–189 (2020)

    Google Scholar 

Download references

Acknowledgement

This work is supported in part by the Project, Grant No. BMKY2019B04-1 and the Strategic Priority Research Program of Chinese Academy of Sciences, Grant No. XDC02040400.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jing Ya .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Ya, J., Liu, T., Guo, L. (2020). A Compare-Aggregate Model with External Knowledge for Query-Focused Summarization. In: Huang, Z., Beek, W., Wang, H., Zhou, R., Zhang, Y. (eds) Web Information Systems Engineering – WISE 2020. WISE 2020. Lecture Notes in Computer Science(), vol 12343. Springer, Cham. https://doi.org/10.1007/978-3-030-62008-0_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-62008-0_5

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-62007-3

  • Online ISBN: 978-3-030-62008-0

  • eBook Packages: Computer ScienceComputer Science (R0)