Abbreviated text input using language modeling

@article{Shieber2007AbbreviatedTI,
  title={Abbreviated text input using language modeling},
  author={Stuart M. Shieber and Rani Nelken},
  journal={Natural Language Engineering},
  year={2007},
  volume={13},
  pages={165-183}
}
We address the problem of improving the efficiency of natural language text input under degraded conditions (for instance, on mobile computing devices or by disabled users), by taking advantage of the informational redundancy in natural language. Previous approaches to this problem have been based on the idea of prediction of the text, but these require the user to take overt action to verify or select the system’s predictions. We propose taking advantage of the duality between prediction and… CONTINUE READING

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • We decode the abbreviated text using a statistical generative model of abbreviation, with a residual word error rate of 3.3%.

References

Publications referenced by this paper.
Showing 1-10 of 23 references

Analysis of SMS Efficiency

  • How, Yijue.
  • Unpublished Undergraduate Thesis. National…
  • 2004

Generalized algorithms for constructing statistical language models

  • Allauzen, Cyril, Mohri, Mehryar, Roark, Brian.
  • Pages 40–47 of: Proceedings of the 41st Annual…
  • 2003
3 Excerpts

March). Japanese Input System with Digits: Can Japanese be Input Only with Consonants

  • Tanaka-Ishii, Kumiko, Inutsuka, Yusuke, Takeichi, Masato
  • Proceedings of the Human Language Technology…
  • 2001

A Call for Collaborative Interfaces

  • Shieber, M. Stuart
  • Computing Surveys, 28A (electronic).
  • 1996

Similar Papers

Loading similar papers…