A REFINING METHOD OF OBTAINED ATTRIBUTES TO CHARACTERIZE UNDEFINED CONCEPTS USING SEARCH ENGINE

Noriyuki Okumura, Yuto Hatakoshi

2011

Abstract

In this paper, we propose a method to resolve problems of the attributes obtaining method using WWW search engine characterizing undefined concepts, which do not exist in Concept-base. Concept-base is an key database constituting Word Association Mechanism to perform commonsense judgment. Concept-base was constructed automatically by electronic dictionaries and newspapers. Therefore Concept-base has about 120,000 statically defined concepts. Nevertheless, it has no effective learning system. This paper proposes a method to make Concept-base to learn concepts dynamically using Auto Feedback system. In addition, a removal method of noise at-tributes is also proposed. We present attributes refinement method that paid attention to changing with time of the Internet. Furthermore, we inspect the effectiveness by an evaluation experiment.

References

  1. Gordon, J., Van Durme, B. D., and Schubert, L. K. (2010). Learning from the web: Extracting general world knowledge from noisy text. In Proceedings of the AAAI 2010 Workshop on Collaboratively-built Knowledge Sources and Artificial Intelligence.
  2. Gulla, J. A., Borch, H. O., and Ingvaldsen, J. E. (2007). Ontology learning for search applications. In Proceedings of the 2007 OTM Confederated international conference on On the move to meaningful internet systems: CoopIS, DOA, ODBASE, GADA, and IS - Volume Part I, OTM'07, pages 1050-1062, Berlin, Heidelberg. Springer-Verlag.
  3. Hatakoshi, Y. (2010). An acquisition method of attributes for unknown words considering time factor. In The 73rd National Convention of Information Processing Society of Japan.
  4. Horiuchi, Y. and Uchida, O. (2011). Extraction of unsteadiness of concept attributes using weblog articles. In Proceedings of the 10th WSEAS international conference on Applied computer and applied computational science, ACACOS'11, pages 137-141, Stevens Point, Wisconsin, USA. World Scientific and Engineering Academy and Society (WSEAS).
  5. Kudo, T., Yamamoto, K., and Matsumoto, Y. (2004). Applying conditional random fields to japanese morphological analysis. In In Proc. of EMNLP, pages 230- 237.
  6. Okumura, N., Yoshimura, E., Watabe, H., and Kawaoka, T. (2007). An association method using conceptbase. In Proceedings of the 11th international conference, KES 2007 and XVII Italian workshop on neural networks conference on Knowledge-based intelligent information and engineering systems: Part I, KES'07/WIRN'07, pages 604-611, Berlin, Heidelberg. Springer-Verlag.
  7. Tsuzi, Y., Hirokazu, W., and Tsukasa, K. (2004). The method of acquisition of the new concept and its attribute using the world wide web. In The 18th Annual Conference of the Japanese Society for Artificial Intelligence.
Download


Paper Citation


in Harvard Style

Okumura N. and Hatakoshi Y. (2011). A REFINING METHOD OF OBTAINED ATTRIBUTES TO CHARACTERIZE UNDEFINED CONCEPTS USING SEARCH ENGINE . In Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: SSW, (IC3K 2011) ISBN 978-989-8425-80-5, pages 493-497. DOI: 10.5220/0003697804930497


in Bibtex Style

@conference{ssw11,
author={Noriyuki Okumura and Yuto Hatakoshi},
title={A REFINING METHOD OF OBTAINED ATTRIBUTES TO CHARACTERIZE UNDEFINED CONCEPTS USING SEARCH ENGINE},
booktitle={Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: SSW, (IC3K 2011)},
year={2011},
pages={493-497},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003697804930497},
isbn={978-989-8425-80-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: SSW, (IC3K 2011)
TI - A REFINING METHOD OF OBTAINED ATTRIBUTES TO CHARACTERIZE UNDEFINED CONCEPTS USING SEARCH ENGINE
SN - 978-989-8425-80-5
AU - Okumura N.
AU - Hatakoshi Y.
PY - 2011
SP - 493
EP - 497
DO - 10.5220/0003697804930497