Advertisement

Sentence Compression Using Statistical Information About Dependency Path Length

  • Kiwamu Yamagata
  • Satoshi Fukutomi
  • Kazuyuki Takagi
  • Kazuhiko Ozeki
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4188)

Abstract

This paper is concerned with the use of statistical information about dependency path length for sentence compression. The sentence compression method employed here requires a quantity called inter-phrase dependency strength. In the training process, original sentences are parsed, and the number of tokens is counted for each pair of phrases, connected with each other by a dependency path of certain length, that survive as a modifier-modified phrase pair in the corresponding compressed sentence in the training corpus. The statistics is exploited to estimate the inter-phrase dependency strength required in the sentence compression process. Results of subjective evaluation shows that the present method outperforms the conventional one of the same framework where the distribution of dependency distance is used to estimate the inter-phrase dependency strength.

Keywords

Dependency Structure Dependency Path Compression Rate Training Corpus Test Sentence 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Okumura, M., Nanba, H.: Automated text summarization: A survey. Journal of Natural Language Processing 6(6), 1–26 (1999)Google Scholar
  2. 2.
    Oguro, R., Ozeki, K., Zhang, Y., Takagi, K.: An efficient algorithm for Japanese sentence compaction based on phrase importance and inter-phrase dependency. In: Sojka, P., Kopeček, I., Pala, K. (eds.) TSD 2000. LNCS (LNAI), vol. 1902, pp. 65–81. Springer, Heidelberg (2000)Google Scholar
  3. 3.
    Oguro, R., Sekiya, H., Morooka, Y., Takagi, K., Ozeki, K.: Evaluation of a Japanese sentence compression method based on phrase significance and inter-phrase dependency. In: Sojka, P., Kopeček, I., Pala, K. (eds.) TSD 2002. LNCS (LNAI), vol. 2448, pp. 27–32. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  4. 4.
  5. 5.
  6. 6.
    Fukutomi, S., Takagi, K., Ozeki, K.: Aligning phrases in original text and its summary using concept distance and inter-phrase dependency. In: Proc. 67th Annual Meeting of IPSJ, vol. 2, pp. 119–120 (2005)Google Scholar
  7. 7.
    Morooka, Y., Esaki, M., Takagi, K., Ozeki, K.: Summarization of newspaper articles using important sentence extraction and sentence compression. In: Proc. 10th Annual Meeting of Natural Language Processing Society, pp. 436–439 (2004)Google Scholar
  8. 8.
    Sinbunsha, M.: Mainichi Shinbun zenbun-kiji oyobi 54-moji database (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Kiwamu Yamagata
    • 1
  • Satoshi Fukutomi
    • 1
  • Kazuyuki Takagi
    • 1
  • Kazuhiko Ozeki
    • 1
  1. 1.The University of Electro-CommunicationsTokyoJapan

Personalised recommendations