Abstract
Evaluating systems that correct errors in non-native writing is difficult because of the possibility of multiple correct answers and the variability in human agreement. This paper seeks to improve the best practice of such evaluation by analyzing the frequency of multiple correct answers and identifying factors that influence agreement levels in judging the usage of articles and noun number. © 2009 The Association for Computational Linguistics.
| Original language | English |
|---|---|
| Title of host publication | ACL-IJCNLP 2009 - LAW 2009: 3rd Linguistic Annotation Workshop, Proceedings |
| Pages | 60-63 |
| Publication status | Published - 2009 |
| Externally published | Yes |
| Event | 3rd Linguistic Annotation Workshop, LAW 2009 - Suntec, Singapore Duration: 6 Aug 2009 → 7 Aug 2009 |
Conference
| Conference | 3rd Linguistic Annotation Workshop, LAW 2009 |
|---|---|
| Place | Singapore |
| City | Suntec |
| Period | 6/08/09 → 7/08/09 |
Fingerprint
Dive into the research topics of 'Human evaluation of article and noun number usage: Influences of context and construction variability'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver