Skip to main content
SpringerLink
Log in

A Theme Allocation for a Sentence Based on Head Driven Patterns

  • Conference paper
Text, Speech and Dialogue (TSD 2005)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 3658))

Included in the following conference series:

Abstract

Since sentences are the basic propositional units of text, knowing their themes should help various tasks requiring the knowledge about the semantic content of text. In this paper, we examine the notion of sentence theme and propose an automatic scheme where head-driven patterns are used for theme assignment. We tested our scheme with sentences in encyclopedia articles and obtained a promising result of 98.96% in F-score for training data and 88.57% for testing data, which outperform the baseline.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Cunningham, J.W., Moore, D.M.: The Confused world of main idea. In: Baumann, J.F. (ed.) Teaching main idea, IRA, N.Y (1986)

    Google Scholar 

  2. Fellbaum, C., et al.: WordNet:An eletroic lexical database. The MIT press, IRA (1998)

    Google Scholar 

  3. Yang, Y.: An evaluation of statistical approaches to text categorization, Information retrieval (1998)

    Google Scholar 

  4. Jeong, T.J., Jang, B.T.: Web Information search using reinforcement learning. In: Proceedings of the Korean information science society conference (KISS) (2001)

    Google Scholar 

  5. Park, K.R., Jang, E.J., Park, S.G.: Improved link analysis algorithm using document feature information. In: KISS 2003 (2003)

    Google Scholar 

  6. Lee, S.E., Hwang, I.J.: Summarizing relevant web pages based on semantic region. In: KISS 2003 (2003)

    Google Scholar 

  7. Seo, H.: A Study on the structure and theme-construction of Korean discourses, Ph.D dissertation, Seoul National University (2002)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Engineering, Information and Communications University, 119, Munji-ro, Yuseong-gu, Daejeon, 305-732, Republic of Korea

    Bo-Yeong Kang & Sung-Hyon Myaeng

Authors
  1. Bo-Yeong Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sung-Hyon Myaeng
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Computer Science, University of West Bohemia in Pilsen, Univerzitni 8, 30614, Plzen, Czech Republic

    Václav Matoušek , Pavel Mautner  & Tomáš Pavelka ,  & 

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kang, BY., Myaeng, SH. (2005). A Theme Allocation for a Sentence Based on Head Driven Patterns. In: Matoušek, V., Mautner, P., Pavelka, T. (eds) Text, Speech and Dialogue. TSD 2005. Lecture Notes in Computer Science(), vol 3658. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11551874_24

Download citation

  • DOI: https://doi.org/10.1007/11551874_24

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-28789-6

  • Online ISBN: 978-3-540-31817-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation