Evaluating an NLG System using Post-Editing
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 1700-1700.
Abstract
Computer-generated texts, whether from Natural Language Generation (NLG) or Machine Translation (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 that produces weather forecasts.
Somayajulu Sripada, Ehud Reiter, and Lezan Hawizy. 2005. Evaluating an NLG System using Post-Editing. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05. IJCAI, 1700–1700. https://ijcai.org/proceedings/2005/297
Sripada, S., Reiter, E., & Hawizy, L. (2005). Evaluating an NLG System using Post-Editing. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 (pp. 1700–1700). IJCAI. https://ijcai.org/proceedings/2005/297
@inproceedings{ijcai2005p297,
title = {Evaluating an NLG System using Post-Editing},
author = {Sripada, Somayajulu and Reiter, Ehud and Hawizy, Lezan},
booktitle = {Proceedings of the Nineteenth International Joint Conference on
Artificial Intelligence, {IJCAI-05}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {1700--1700},
year = {2005},
url = {https://ijcai.org/proceedings/2005/297},
}
TY - CPAPER TI - Evaluating an NLG System using Post-Editing AU - Sripada, Somayajulu AU - Reiter, Ehud AU - Hawizy, Lezan T2 - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 PB - International Joint Conferences on Artificial Intelligence PY - 2005 SP - 1700 EP - 1700 UR - https://ijcai.org/proceedings/2005/297 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
