Advertisement

Technical Trend Analysis by Analyzing Research Papers’ Titles

  • Tomoki Kondo
  • Hidetsugu Nanba
  • Toshiyuki Takezawa
  • Manabu Okumura
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6562)

Abstract

The history of the elemental technologies (underlying technologies) used in a particular research field is essential for analyzing technical trend in the field. However, it is too costly and time-consuming to collect and read all of the papers in the field for the purpose of this analysis. Therefore, we have constructed a system that can recognize the application of elemental technologies to any research field. We focus on the structure of research papers’ titles for the extraction of elemental technologies. In research papers’ titles, particular expressions, such as "using" or "is based on", are often used. The terms immediately after these expressions are considered elemental technologies. Therefore, we used these expressions as cue phrases, and extracted elemental technologies from both English and Japanese titles. We conducted experiments to investigate the effectiveness of our method for analyzing the structure of titles. We obtained Recall and Precision scores of 0.825 and 0.816, respectively, for the analysis of Japanese titles, and scores of 0.735 and 0.780, respectively, for English titles. Finally, we constructed a system that creates a technical trend map for a given research field.

Keywords

technical trend analysis information extraction machine translation machine learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Elkiss, A., Shen, S., Fader, A., Erkan, G., States, D., Radev, D.: Blind Men and Elephants: What do Citation Summaries Tell Us about a Research Article? Journal of the American Society for Information Science and Technology 59(1), 51–62 (2007)CrossRefGoogle Scholar
  2. 2.
    Kando, N., Kuriyama, K., Nozue, T., Eguchi, K., Kato, H., Hidaka, S.: Overview of IR Tasks at the first NTCIR Workshop. In: Proc. the 1st NTCIR Workshop on Research in Japanese Text Retrieval and Term Recognition, pp. 11–44 (1999)Google Scholar
  3. 3.
    Kando, N., Kuriyama, K., Yoshioka, M.: Overview of Japanese and English Information Retrieval Tasks (JEIR) at the second NTCIR Workshop. In: Proc. the 2nd NTCIR Workshop Meeting, pp. 4-37–4-60 (2001)Google Scholar
  4. 4.
    Mohammad, S., Dorr, B., Egan, M., Hassan, A., Muthukrishan, P., Qazvinian, V., Radev, D., Zajic, D.: Generating Surveys of Scientific Paradigms. In: Proc. HLT-NAACL 2009 (2009)Google Scholar
  5. 5.
    Nanba, H. and Okumura, M.: Towards Multi-paper Summarization Using Reference Information. In: Proc. the 16th International Joint Conferences on Artificial Intelligence, pp. 926–931 (1999) Google Scholar
  6. 6.
    Taniguchi, Y., Nanba, H.: Identification of Bibliographic Information Written in both Japanese and English. In: Christensen-Dalsgaard, B., Castelli, D., Ammitzbøll Jurik, B., Lippincott, J. (eds.) ECDL 2008. LNCS, vol. 5173, pp. 431–433. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  7. 7.
    Teufel, S., Moens, M.: Summarizing Scientific Articles: Experiments with Relevance and Rhetorical Status. Computational Linguistics 28(4), 409–445 (2002)CrossRefGoogle Scholar
  8. 8.
    Zitouni, I., Florian, R.: Mention Detection Crossing the Language Barrier. In: Proceedings of Conference on Empirical Methods on Natural Language Processing (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Tomoki Kondo
    • 1
  • Hidetsugu Nanba
    • 1
  • Toshiyuki Takezawa
    • 1
  • Manabu Okumura
    • 2
  1. 1.Graduate School of Information SciencesHiroshima City UniversityAsaminamikuJapan
  2. 2.Precision and Intelligence LaboratoryTokyo Institute of TechnologyMidorikuJapan

Personalised recommendations