{"type":"ScholarlyArticle","title":"Evaluating an NLG System using Post-Editing","authors":[{"name":"Somayajulu Sripada","slug":"somayajulu-sripada","given":"Somayajulu","family":"Sripada","affiliation":""},{"name":"Ehud Reiter","slug":"ehud-reiter","given":"Ehud","family":"Reiter","affiliation":""},{"name":"Lezan Hawizy","slug":"lezan-hawizy","given":"Lezan","family":"Hawizy","affiliation":""}],"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.","doi":null,"url":"https://ijcai.org/proceedings/2005/297","pdf":"https://ijcai.org/proceedings/2005/0297.pdf","markdown":"https://ijcai.org/proceedings/2005/297.md","bibtex":"https://ijcai.org/proceedings/2005/bibtex/297","volume":{"slug":"2005","title":"Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2005","url":"https://ijcai.org/proceedings/2005/","year":2005,"location":"Edinburgh, Scotland, UK","dates":"","editors":"","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":297,"pages":{"first":1700,"last":1700},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}