Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Citation-based Article Summarization using a Combination of Lexical Text Similarities: Evaluation with Computational Linguistics Literature Summarization Datasets

  • Kang, In-Su (Dept. of Computer Science, Kyungsung University)
  • Received : 2019.06.05
  • Accepted : 2019.07.28
  • Published : 2019.07.31
Download PDF
⟨ Previous Next ⟩

Abstract

Citation-based article summarization is to create a shortened text for an academic article, reflecting the content of citing sentences which contain other's thoughts about the target article to be summarized. To deal with the problem, this study introduces an extractive summarization method based on calculating a linear combination of various sentence salience scores, which represent the degrees to which a candidate sentence reflects the content of author's abstract text, reader's citing text, and the target article to be summarized. In the current study, salience scores are obtained by computing surface-level textual similarities. Experiments using CL-SciSumm datasets show that the proposed method parallels or outperforms the previous approaches in ROUGE evaluations against SciSumm-2017 human summaries and SciSumm-2016/2017 community summaries.

Keywords

Table 1. ROUGE-2 F1 Performances of Different Summarization Methods

CPTSCQ_2019_v24n7_31_t0001.png 이미지

References

  1. V. Qazvinian, and D. Radev, "Scientific Paper Summarization Using Citation Summary Networks," Proceedings of COLING-2008, pp. 689-696, 2008.
  2. A. Abu-Jbara, and D. Radev, "Coherent Citation-Based Summarization of Scientific Papers," Proceedings of ACL-2011, pp. 500-509, 2011.
  3. K. Jaidka, M. Chandrasekaran, S. Rustagi, and M.-Y. Kan, "Overview of the CL-SciSumm 2016 Shared Task," Proceedings of BIRNDL-2016, pp. 93-102, 2016.
  4. K. Jaidka, M. Chandrasekaran, D. Jain, and M.-Y. Kan, "The CL-SciSumm Shared Task 2017: Results and Key Insights," Proceedings of BIRNDL-2017, pp. 1-15, 2017.
  5. K. Jaidka, M. Yasunaga, M. Chandrasekaran, D. Radev, and M.-Y. Kan, "The CL-SciSumm Shared Task 2018: Results and Key Insights," Proceedings of BIRNDL-2018, pp. 74-83, 2018.
  6. A. Abura'ed, A. Bravo, L. Chiruzzo, and H. Saggion, "LaSTUS/TALN+INCO @ CL-SciSumm 2018 - Using Regression and Convolutions for Cross-document Semantic Linking and Summarization of Scholarly Literature," Proceedings of BIRNDL-2018, pp. 150-163, 2018.
  7. M. Yasunaga, J. Kasai, R. Zhang, A. Fabbri, I. Li, D. Friedman, and D. Radev, "ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks," Proceedings of AAAI-2019, 2019.
  8. H. Saggion, A. AbuRa'ed, and F. Ronzano, "Trainable Citation-enhanced Summarization of Scientific Articles," Proceedings of BIRNDL-2016, pp. 175-186, 2016.
  9. L. Li, L. Mao, Y. Zhang, J. Chi, T. Huang, X. Cong, and H. Peng, "CIST System for CL-SciSumm 2016 Shared Task," Proceedings of BIRNDL-2016, pp. 156-167, 2016.
  10. L. Li, Y. Zhang, L. Mao, J. Chi, M. Chen, and Z. Huang, "CIST@CLSciSumm-17: Multiple Features Based Citation Linkage, Classification and Summarization," Proceedings of BIRNDL-2017, pp. 43-54, 2017.
  11. A. Abura'ed, L. Chiruzzo, H. Saggion, P. Accuosto, and A. Bravo, "LaSTUS/TALN @ CLSciSumm-17: Cross-document Sentence Matching and Scientific Text Summarization Systems," Proceedings of BIRNDL-2017, pp. 55-66, 2017.
  12. S. Ma, H. Zhang, J. Xu, and C. Zhang, "NJUST @ CLSciSumm-18," Proceedings of BIRNDL-2018, pp. 114-129, 2018.
  13. L. Li, J. Chi, M. Chen, Z. Huang, Y. Zhu, and X. Fu, "CIST@CLSciSumm-18: Methods for Computational Linguistics Scientific Citation Linkage, Facet Classification and Summarization," Proceedings of BIRNDL-2018, pp. 84-95, 2018.
  14. Z. Cao, W. Li, and D. Wu, "PolyU at CL-SciSumm 2016," Proceedings of BIRNDL-2016, pp. 132-138, 2016.
  15. A. Lauscher, G. Glavas, and K. Eckert, "University of Mannheim @ CLSciSumm-17: Citation-Based Summarization of Scientific Articles Using Semantic Textual Similarity," Proceedings of BIRNDL-2017, pp. 33-42, 2017.
  16. A. Cohan, and N. Goharian, "Scientific Document Summarization via Citation Contextualization and Scientific Discourse," International Journal on Digital Libraries, Vol. 19, No. 2-3, pp. 287-303, 2018. https://doi.org/10.1007/s00799-017-0216-8
  17. S. Ma, J. Xu, J. Wang, and C. Zhang, "NJUST @ CLSciSumm-17," Proceedings of BIRNDL-2017, pp. 16-25, 2017.
  18. B. Malenfant, and G. Lapalme, "RALI System Description for CL-SciSumm 2016 Shared Task," Proceedings of BIRNDL-2016, pp. 146-155, 2016.
  19. Q. Mei, and C. Zhai, "Generating Impact-Based Summaries for Scientific Literature," Proceedings of ACL-2008, pp. 816-824, 2008.
  20. J. Conroy, and S. Davis, "Section Mixture Models for Scientific Document Summarization," International Journal on Digital Libraries, Vol. 19, No. 2-3, pp. 305-322, 2018. https://doi.org/10.1007/s00799-017-0218-6
  21. D. Debnath, A. Achom, and P. Pakray, "NLP-NITMZ @ CLScisumm-18," Proceedings of BIRNDL-2018, pp. 164-171, 2018.
  22. L. Moraes, S. Baki, R. Verma, and D. Lee, "University of Houston at CL-SciSumm 2016: SVMs with tree kernels and Sentence Similarity," Proceedings of BIRNDL-2016, pp. 113-121, 2016.
  23. R. Day, "The Origins of the Scientific Paper: The IMRAD Format," American Medical Writers Association Journal, Vol. 4, No. 2, pp. 16-18. 1989.
  24. P. Jaccard, "Nouvelles recherches sur la distribution florale," Bull. Soc. Vaud. Sci. Nat., Vol. 44, pp. 223-270, 1908.
  25. C.-Y. Lin, "ROUGE: A Package for Automatic Evaluation of Summaries," Proceedings of Workshop on Text Summarization Branches Out, pp. 74-81, 2004.
  26. P. Mayr, M. Chandrasekaran, and K. Jaidka, "Report on the 3rd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2018)," SIGIR Forum 52(2), pp. 105-110, 2018.