Top > JACIII > Tag Line Generating System Using Information on the Web

single-jc.php

JACIII Vol.17 No.2 pp. 185-193
doi: 10.20965/jaciii.2013.p0185
(2013)

Paper:

Views over last 60 days: 601

Tag Line Generating System Using Information on the Web

Hiroaki Yamane and Masafumi Hagiwara

The Department of Information and Computer Science, Keio University, 3-14-1 Hiyoshi, Kohoku-ku, Yokohama 223-8522, Japan

Received:
November 17, 2012
Accepted:
January 28, 2013
Published:
March 20, 2013
Creative Commons License
Keywords:
sentence generation, tag lines, web information, text mining, N-gram
Abstract
This paper proposes a tag line generating systemusing information extracted from the web. Tag lines sometimes attract attention even when they consist of indirect word group of the target. We use web information to extract hidden data and use several tag line corpora to collect a large number of tag lines. First, knowledge related to the input is obtained from the web. Then, the proposed system selects suitable words according to the theme. Also, model tag lines are selected from the corpora using the knowledge. By inserting nouns, verbs and adjectives into model tag lines’ structure, candidate sentences are generated. These tag line candidates are selected by the suitability as a sentence using a text N-gram corpus. The subjective experiment measures the quality of system-generated tag lines and some of them are quite comparable to human-made ones.
Cite this article as:
H. Yamane and M. Hagiwara, “Tag Line Generating System Using Information on the Web,” J. Adv. Comput. Intell. Intell. Inform., Vol.17 No.2, pp. 185-193, 2013.
Data files:
References
  1. [1] Y. Anzai, “Mind And Brain – introduction of cognitive science,” Iwanami Shinsho, 2011 (in Japanese).
  2. [2] H. Koizumi, “Science history of brain – From Freud to brain map to MRI,” Kadokawa SSC Shinsho, 2011 (in Japanese).
  3. [3] K. Shimizu and M. Hagiwara, “A new electronic dictionary with meaning description of case frame,” J. of Advanced Computational Intelligence and Intelligent Informatics, Vol.9, No.3, pp. 304-313, 2005.
  4. [4] Z. Kozareva, B. Navarro, S. Vazquez, and A. Montoyo, “Ua-zbsa: A headline emotion classification through web information,” In Proc. of the Fourth International Workshop on Semantic Evaluations (SemEval-2007), pp. 334-337, Prague, Czech Republic, June 2007.
  5. [5] A. Abbasi, H. Chen, S. Thoms, and T. Fu, “Affect analysis of web forums and blogs using correlation ensembles,” IEEE Trans. on Knowledge and Data Engineering, Vol.20, pp. 1168-1180, 2008.
  6. [6] C. Kohli, L. Leuthesser, and R. Suri, “Got slogan? guidelines for creating effective slogans,” Business Horizons, Vol.50, No.5, pp. 415-422, 2007.
  7. [7] H. Kitamura, R. Yamaji, and H. Tabuki, “Advertising Slogan,” Yuhikaku, 1981 (in Japanese).
  8. [8] Sloganizer.net, “Instant slogans with our slogan generator.”
    http://www.sloganizer.net/en/
  9. [9] THE-PCMAN-WEBSITE, “Free slogan generator.”
    http://www.thepcmanwebsite.com/media/free_slogan_generator/index.php
  10. [10] M. Banko, V. O. Mittal, and M. J. Witbrock, “Headline generation based on statistical translation,” In Proc. of the 38th Annual Meeting on Association for Computational Linguistics, ACL ’00, pp. 318-325, 2000.
  11. [11] T. Matsudaira and M. Hagiwara, “Catchcopy creation support system using electronic dictionary and genetic programming,” The Trans. of the Institute of Electrical Engineers of Japan, C, A publication of Electronics, Information and System Society, Vol.124, No.1, pp. 164-169, 2004 (in Japanese).
  12. [12] T. Matsudaira and M. Hagiwara, “Catchcopy creation support system using interactive genetic programming and electronic dictionary,” The Trans. of the Institute of Electrical Engineers of Japan, C, A publication of Electronics, Information and System Society, Vol.125, No.4, pp. 616-622, 2005 (in Japanese).
  13. [13] Y. Nishihara, W. Sunayama, and M. Yachida, “Title-composing support system for reaching new audiences,” In The 21st Annual Conf. of the Japanese Society for Artificial Intelligence, pp. 2H4-2H5. The Japanese Society for Artificial Intelligence, 2007 (in Japanese).
  14. [14] S. Nakano and T. Onisawa, “Generation system of attractive tagline,” In Japan Society of Kansei Engineering, p. B71, Japan Society of Kansei Engineering, 2007 (in Japanese).
  15. [15] N. Ito and M. Hagiwara, “Natural language generation using automatically constructed lexical resources,” In Int. Joint Conf. on Neural Networks (IJCNN), The 2011, pp. 980-987, Aug. 2011.
  16. [16] Ministry of Economy, Trade and Industry of Japan, “Technology industry map 2010, software 2 service engineering field,” 2010 (in Japanese).
  17. [17] D. Bollegala, Y. Matsuo, and M. Ishizuka, “A web search enginebased approach to measure semantic similarity between words,” IEEE Trans. on Knowledge and Data Engineering, Vol.23, pp. 977-990, 2011.
  18. [18] S. Kenji and M. Shigeki, “Product retrieval method based on customer reviews,” IPSJ Journal, Vol.49, No.7, pp. 2598-2603, Jul. 2008 (in Japanese).
  19. [19] H. Yamane and M. Hagiwara, “Catchphrase generating system based on statistical analysis,” SIG-KBS Workshop, Vol.94, pp. 7-12, Dec. 2011 (in Japanese).
  20. [20] NTT Comware, “Nippon long-seller discussion Vol.73 arm pencil case ‘an elephant’s step can’t break it!,” (in Japanese).
    http://www.nttcom.co.jp/comzine/no073/long seller/index.html
  21. [21] SourceForge.jp, “Ipadic legacy,” (in Japanese).
    http://sourceforge.jp/projects/ipadic/releases/
  22. [22] T. Kudo, K. Yamamoto, and Y. Matsumoto, “Applying conditional random fields to japanese morphological analysis,” In Proc. of EMNLP, pp. 230-237, 2004.
  23. [23] T. Kudo and H. Kazawa, “Web Japanese N-gram Version 1,” Gengo Shigen Kyokai, 2007 (in Japanese).
  24. [24] T. Kudo and H. Kazawa, “Release of Large-scale Japanese N-gram Data,” 2007 (in Japanese).
    http://googlejapan.blogspot.com/2007/11/n-gram.html

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Apr. 18, 2024