Abstract
Currently there is little agreement about, or even discussion of, methodologies for taskbased evaluation of NLG systems. I discuss one specific issue in this area, namely the importance of control vs the importance of ecological validity (real-world context), and suggest that perhaps we need to put more emphasis on ecological validity in NLG evaluations.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of UCNLG+Eval 2011 |
| Publisher | Association for Computational Linguistics |
| Pages | 28-32 |
| Number of pages | 5 |
| Publication status | Published - 2011 |
| Event | UCNLG+Eval: Language Generation and Evaluation Workshop - Edinburgh, United Kingdom Duration: 21 Jul 2011 → … |
Conference
| Conference | UCNLG+Eval: Language Generation and Evaluation Workshop |
|---|---|
| Country/Territory | United Kingdom |
| City | Edinburgh |
| Period | 21/07/11 → … |