ML Anthology

Evaluating an NLG System Using Post-Editing

Somayajulu Sripada, Ehud Reiter, Lezan Hawizy
IJCAI 2005 pp. 1700-1701
/ijcai/2005/sripada2005ijcai-evaluating/

Abstract

(MT) systems, are often post-edited by humans before being released to users. The frequency and type of post-edits is a measure of how well the system works, and can be used for evaluation. We describe how we have used post-edit data to evaluate SUMTIME-MOUSAM, an NLG system

PDF Semantic Scholar

Cite

Text

Sripada et al. "Evaluating an NLG System Using Post-Editing." International Joint Conference on Artificial Intelligence, 2005.

Markdown

[Sripada et al. "Evaluating an NLG System Using Post-Editing." International Joint Conference on Artificial Intelligence, 2005.](https://mlanthology.org/ijcai/2005/sripada2005ijcai-evaluating/)

BibTeX

@inproceedings{sripada2005ijcai-evaluating,
  title     = {{Evaluating an NLG System Using Post-Editing}},
  author    = {Sripada, Somayajulu and Reiter, Ehud and Hawizy, Lezan},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2005},
  pages     = {1700-1701},
  url       = {https://mlanthology.org/ijcai/2005/sripada2005ijcai-evaluating/}
}