Skip to main content
View expanded cover

NII Conference on Testbeds and Community for Information Access Research

NTCIR 2019: NII Testbeds and Community for Information Access Research pp 97–109Cite as

Automatic Training Data Construction and Extractive Supervised Summarization for NTCIR-14 QA Lab-PoliInfo

  • 205 Accesses

Part of the Lecture Notes in Computer Science book series (LNISA,volume 11966)

Abstract

On the summarization task at NTCIR-14 QA Lab-PoliInfo, participants of the task need to generate a summary corresponding to an assembly member speech in assembly minutes within the limit length. Our method extracts important sentences to summarize an assembly member speech in the minutes. Our method applies a machine learning model to predict the important sentences. However, the given assembly minutes’ data do not contain information about the importance of the sentences. As a result, we cannot directly utilize machine learning techniques for the task. Therefore, we construct training data for the importance prediction model using a word similarity between sentences in a speech and those in the summary. In addition, we apply the sentence reduction process. In the process, we consider characteristics of summaries of assembly minutes to avoid removal of important words in extracted sentences. On the evaluation, all the scores by our supervised method with the constructed data outperformed unsupervised and supervised baseline methods. The result shows the effectiveness of our method.

Keywords

  • Extractive summarization
  • Sentence extraction
  • Automatic dataset construction
  • Sentence reduction
  • Machine learning

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-36805-0_8
  • Chapter length: 13 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   44.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-36805-0
  • 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   59.99
Price excludes VAT (USA)
Learn about institutional subscriptions
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.

References

  1. Hiai, S., Otani, Y., Yamamura, T., Shimada, K.: KitAi-PI: summarization system for NTCIR-14 QA Lab-Poliinfo. In: Proceedings of The 14th NTCIR Conference on Evaluation of Information Access Technologies (2019)

    Google Scholar 

  2. Katragadda, R., Pingali, P., Varma, V.: Sentence position revisited: a robust light-weight update summarization baseline algorithm. In: Proceedings of the Third International Workshop on Cross Lingual Information Access: Addressing the Information Need of Multilingual Societies (CLIAWS3), pp. 46–52 (2009)

    Google Scholar 

  3. Kimura, T., Tagami, R., Katsuyama, H., Sugimoto, S., Miyamori, H.: KSU systems at the NTCIR-14 QA Lab-Poliinfo task. In: Proceedings of The 14th NTCIR Conference on Evaluation of Information Access Technologies (2019)

    Google Scholar 

  4. Kimura, Y., et al.: Overview of the NTCIR-14 QA Lab-Poliinfo task. In: Proceedings of the 14th NTCIR Conference on Evaluation of Information Access Technologies (2019)

    Google Scholar 

  5. Kiyota, Y., Kurohashi, S.: Automatic summarization of Japanese sentences and its application to a WWW KWIC index. In: Proceedings of 2001 Symposium on Applications and the Internet (2001)

    Google Scholar 

  6. Kubo, T.: MeCab: yet another part-of-speech and morphological analyzer. http://mecab.sourceforge.net/

  7. Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Proceedings of the Eighth Workshop on the Annual Meeting of the Association for Computational Linguistics (ACL-04), pp. 74–81 (2004)

    Google Scholar 

  8. Mihalcea, R., Tarau, P.: TextRank: bringing order into text. In: Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (2004)

    Google Scholar 

  9. Mikami, M., Masuyama, S., Nakagawa, S.: A summarization method by reducing redundancy of each sentence for making captions of newscasting. J. Nat. Lang. Process. 6(6), 65–91 (1999)

    CrossRef  Google Scholar 

  10. Ogawa, Y., Satou, M., Komamizu, T., Toyama, K.: nagoy team’s summarization system at the NTCIR-14 QA Lab-Poliinfo. In: Proceedings of The 14th NTCIR Conference on Evaluation of Information Access Technologies (2019)

    Google Scholar 

  11. Ouyang, Y., Li, W., Lu, Q., Zhang, R.: A study on position information in document summarization. In: Proceedings of the 23rd International Conference on Computational, pp. 919–927 (2010)

    Google Scholar 

  12. Shinjo, T., Nishikawa, H., Tokunaga, T.: TTECH at the NTCIR-14 QA Lab-Poliinfo task. In: Proceedings of The 14th NTCIR Conference on Evaluation of Information Access Technologies (2019)

    Google Scholar 

  13. Tang, L., Watanabe, K., Yada, S., Kageura, K.: LisLb-Team at the NTCIR-14 QA Lab-Poliinfo task. In: Proceedings of The 14th NTCIR Conference on Evaluation of Information Access Technologies (2019)

    Google Scholar 

  14. Terazawa, K., Shirato, D., Akiba, T., Masuyama, S.: AKBL at the NTCIR-14 QA Lab-Poliinfo task. In: Proceedings of The 14th NTCIR Conference on Evaluation of Information Access Technologies (2019)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Artificial Intelligence, Kyushu Institute of Technology, Fukuoka, Japan

    Satoshi Hiai, Yuka Otani, Takashi Yamamura & Kazutaka Shimada

Authors
  1. Satoshi Hiai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuka Otani
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Takashi Yamamura
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kazutaka Shimada
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Satoshi Hiai .

Editor information

Editors and Affiliations

  1. University of Tsukuba, Tsukuba, Japan

    Makoto P. Kato

  2. Tsinghua University, Beijing, China

    Prof. Yiqun Liu

  3. National Institute of Informatics (NII), Tokyo, Japan

    Prof. Noriko Kando

  4. University of Waterloo, Waterloo, ON, Canada

    Charles L. A. Clarke

Rights and permissions

Reprints and Permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Hiai, S., Otani, Y., Yamamura, T., Shimada, K. (2019). Automatic Training Data Construction and Extractive Supervised Summarization for NTCIR-14 QA Lab-PoliInfo. In: Kato, M., Liu, Y., Kando, N., Clarke, C. (eds) NII Testbeds and Community for Information Access Research. NTCIR 2019. Lecture Notes in Computer Science(), vol 11966. Springer, Cham. https://doi.org/10.1007/978-3-030-36805-0_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-36805-0_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-36804-3

  • Online ISBN: 978-3-030-36805-0

  • eBook Packages: Computer ScienceComputer Science (R0)