Abstract
We developed a summarizing system ABISYS based on the output of semantic analysis system SAGE. ABISYS extracts important words from an article and generates summary sentences according to the word meanings and the deep cases among the words in the output from SAGE. In this paper, we define five kinds of scores to evaluate the importance of a word respectively on repetition information, context information, position information, opinion word information and topic-focus information. We first calculate the above scores for each substantive and reflect them in a five-dimensional space. Then the probability of each substantive to be important is calculated using a pan-distance of Mahalanobis. Finally, we complement the indispensable cases for verbs and the Sahen nouns that have been selected as important words, and use them as the summary element words to generate easy-to-read Japanese sentences. We carried out a subjectivity evaluation for our system output by referring to the summaries made by human. In comparison with the subjectivity evaluations made for other summarizing systems, we found that the point of readability was on a par with other systems, while the point of content covering was much better. And 95% of the summary sentences generated by ABISYS were acknowledged as correct Japanese sentences.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hahn, U., Reimer, U.: Topic essentials. In: Proceedings of the 11th COLING, Bonn, Germany, pp. 497–503 (1986)
Harada, M., Mizuno, T.: Japanese semantic analysis system SAGE using EDR. Transactions of the Japanese Society of Artificial Intelligence 16(1), 85–93 (2001) (in Japanese)
Harada, M., Tabuchi, K., Oono, H.: Improvement of speed and accuracy of Japanese semantic analysis system SAGE and its accuracy evaluation by comparison with EDR corpus. Transactions of Information Processing Society of Japan 43(9), 2894–2902 (2002) (in Japanese)
Hatayama, M., Matsuo, Y., Shirai, S.: Summarizing newspaper articles using extracted informative and functional words. Journal of Natural Language Processing 9(4), 55–70 (2002) (in Japanese)
Hovy, E.H., Lin, C.: Automated text summarization in SUMMARIST. In: Proceedings of the ACL 1997/EACL 1997 Workshop on Intelligent Scalable Text Summarization, Madrid, Spain (1997)
Ishizako, Y., Kataoka, A., Masuyama, S., Nakagawa, S.: Summarization by reducing overlaps and its application to TV news texts. SIG Notes NL-133, 45–52 (1999) (in Japanese)
Kawabata, T., Harada, M.: Development research on system InSeRA which analyzes the semantic relations between Japanese sentences. SIG Notes NL-142, 105–112 (2001) (in Japanese)
Kurohasi, S., Nagao, M.: Nihongo Koubun Kaiseki System KNP manual, version 2.0b6 (1998), http://www.kc.t.u-tokyo.ac.jp/nl-resource/index.html
Maezawa, T., Menrai, M., Ueno, M., Han, D., Harada, M.: Improvement of the precision of the semantic analysis system SAGE, and generation of conceptual graph. In: Proceedings of the 66th National Conference of Information Processing Society of Japan, vol. 2, pp. 177–178 (2004) (in Japanese)
Matsumoto etc. Morphological analysis system chasen version 2.2.8 manual (1999), http://chasen.aist-nara.ac.jp/hiki/chasen
Minami, A., Harada, M.: Development of anaphoric analysis system which uses similarity of vocabulary. In: Proceedings of the 64th National Conference of Information Processing Society of Japan, vol. 2, pp. 53–54 (2002) (in Japanese)
Nanba, H., Okumura, M.: Analysis of the results and evaluation methods of text summarization challenge (TSC), a subtask of NTCIR Workshop 2. Technical Report of IEICE, NLC2001-28, pp. 46-52, (2001) (in Japanese)
Oguro, R., Ozeki, K., Zhang, Y., Takagi, K.: A Japanese sentence compaction algorithm based on phrase significance and inter-phrase dependency. Journal of Natural Language Processing 8(3), 3–18 (2001) (in Japanese)
Ohtake, K., Okamoto, D., Kodama, M., Masuyama, S.: A summarization system YELLOW for Japanese newspaper articles. Transactions of Information Processing Society of Japan 43 SIG2 , 37–47 (2002) (in Japanese)
Okumura, M., Nanba, H.: Automated text summarization: a survey. Journal of Natural Language Processing 6(6), 1–26 (1999) (in Japanese)
Okumura, M., Nanba, H.: New topics on automated text summarization. Journal of Natural Language Processing 9(4), 97–116 (2002) (in Japanese)
Sakuma, M.: Bunshou Kouzou To Youyakubun No Showou (Version 3). Kurosio Publisher (2000) (in Japanese)
Ueda, Y., Oka, M., Koyama, T., Miyauchi, T.: Development and evaluation of a summarization system based on phrase-representation summarization method. Journal of Natural Language Processing 9(4), 75–96 (2002) (in Japanese)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Han, D., Noguchi, T., Yago, T., Harada, M. (2005). Summary Generation Centered on Important Words. In: Myaeng, S.H., Zhou, M., Wong, KF., Zhang, HJ. (eds) Information Retrieval Technology. AIRS 2004. Lecture Notes in Computer Science, vol 3411. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-31871-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-31871-2_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25065-4
Online ISBN: 978-3-540-31871-2
eBook Packages: Computer ScienceComputer Science (R0)