Statistically-constrained shallow text marking: techniques, evaluation paradigm and results

@inproceedings{Murphy2007StatisticallyconstrainedST,
  title={Statistically-constrained shallow text marking: techniques, evaluation paradigm and results},
  author={Brian Murphy and Carl Vogel},
  booktitle={Security, Steganography, and Watermarking of Multimedia Contents},
  year={2007}
}
We present three natural language marking strategies based on fast and reliable shallow parsing techniques, and on wide ly available lexical resources: lexical substitution, adjec tiv conjunction swaps, and relativiser switching. We test hese techniques on a random sample of the British National Corpus . Individual candidate marks are checked for goodness of structural and semantic fit, using both lexical resources, a nd the web as a corpus. A representative sample of marks is giv en to 25… CONTINUE READING
9 Citations
24 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 24 references

Syntactic information hiding in plain text,”Master’s thesis, Trinity College Dublin, https://www.cs.tcd.ie/research_groups/clg/brian/mur phy01hidingMasters.pdf

  • B. Murphy
  • 2001
Highly Influential
3 Excerpts

At tacks on lexical natural language steganography systems,

  • C. M. Taskiran, U. Topkara, M. Topkarab, E. J. Delp
  • inProceedings of the SPIE International…
  • 2006
1 Excerpt

A method of linguistic steganography based on collocationallyverified synonymy

  • A. Carstairs-McCarthy
  • Lecture Notes in Computer Science
  • 2004

Component-ba sed digital watermarking of chinese texts,

  • Sun Xingming, Luo Gang, Huang Huajun
  • Proceedings of the 3rd International Conference…
  • 2004

Similar Papers

Loading similar papers…