Skip to main content

XIG: Generating from Interchange Format using Mixed Representations

  • Conference paper
  • First Online:
AI*IA 99: Advances in Artificial Intelligence (AI*IA 1999)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1792))

Included in the following conference series:

  • 424 Accesses

Abstract

We present the C-STAR Italian Generator (XIG), a system for generating Italian text from the interlingua content representation (Interchange Format) adopted within the C-STAR II speech to speech translation project. The constraints of the application scenario led us to follow a Mixed Representions approach to text generation and to adopt for the sentence planner an architecture based on cascades of default rules.

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

Access this chapter

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. Balestri M., Lazzaretto S., Salza PL. and Sandri S. The CSELT system for Italian text-to-speech synthesis. In Eurospeech, pages 2091–2094, Berlin, 1993.

    Google Scholar 

  2. Busemann S. Best-first surface realization. In INLGW-8, pages 101–110, Sussex, 1996.

    Google Scholar 

  3. Busemann S. and Horacek H. A flexible shallow approach to text generation. In INLGW-9, Niagara Falls, 1998.

    Google Scholar 

  4. Cancedda N., Kamstrup G. and Pianta E. Sax: Generating hypertext from SADT models. In Proceedings of NLDB’97, Vancouver, 1997.

    Google Scholar 

  5. Pianesi F., Pianta E. and Tovena LM. Comparing methodologies for evaluating the generator in a speech-to-speech translation system. In Proceedings of EWNLG’99, pages 145–154, Toulouse, 1999.

    Google Scholar 

  6. and Tovena 1999]_Pianta E. and Tovena LM. Mixing representation levels: The hybrid approach to automatic text generation. In Proceedings of AISB’99, pages 8–13, Edinburgh, 1999.

    Google Scholar 

  7. Reiter E. Nlg vs. templates. In EWNLG, Leiden, 1995.

    Google Scholar 

  8. Reiter E. and Mellish Ch. Optimizing the costs and benefits of natural language generation. In Proceedings of IJCAI, pages 1164–1169, 1993.

    Google Scholar 

  9. Tovena LM. A user’s point of view on the interlingua IF. Technical Report 9809-01, ITC-IRST, Trento, 1998.

    Google Scholar 

  10. Tovena LM. and Pianta E. Generating felicitous sentences from underspecified semantic representations. In Proceedings of IWCS-3, pages 410–412, Tilburg, The Netherlands, 1999

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2000 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Pianta, E., Tovena, L.M. (2000). XIG: Generating from Interchange Format using Mixed Representations. In: Lamma, E., Mello, P. (eds) AI*IA 99: Advances in Artificial Intelligence. AI*IA 1999. Lecture Notes in Computer Science(), vol 1792. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46238-4_21

Download citation

  • DOI: https://doi.org/10.1007/3-540-46238-4_21

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-67350-7

  • Online ISBN: 978-3-540-46238-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics