TARA: Quality Estimation: an experimental study using unsupervised similarity measures

Home

Submit

Alerts

Academic/Research Units
& Collections

Title

Author

By Date of Publication

Subject

Sponsors

TARA >
School of Computer Science and Statistics >
Computer Science >
Computer Science (Scholarly Publications) >

Please use this identifier to cite or link to this item: http://hdl.handle.net/2262/64203

Title:	Quality Estimation: an experimental study using unsupervised similarity measures
Other Titles:	Proceedings of the 7th Workshop on Statistical Machine Translation
Author:	MOREAU, ERWAN VOGEL, CARL
Sponsor:	Science Foundation Ireland
Author's Homepage:	http://people.tcd.ie/vogel
Keywords:	computational linguistics text classification quality estimation machine learning
Issue Date:	2012
Publisher:	The Association for Computational Linguistics (ACL)
Citation:	Erwan Moreau and Carl Vogel, Quality Estimation: an experimental study using unsupervised similarity measures, Proceedings of the 7th Workshop on Statistical Machine Translation, Montreal, June 7-8, 2012, Chris Callison-Burch, Philipp Koehn, Christof Monz, Matt Post, Radu Soricut, and Lucia Specia, The Association for Computational Linguistics (ACL), 2012, 120 - 126
Abstract:	We present the approach we took for our participation to the WMT12 Quality Estimation Shared Task: our main goal is to achieve reasonably good results without appeal to supervised learning. We have used various similarity measures and also an external resource (Google N-grams). Details of results clarify the interest of such an approach.
Description:	PUBLISHED
URI:	http://hdl.handle.net/2262/64203
Appears in Collections:	Computer Science (Scholarly Publications)

Files in This Item:

File	Description	Size	Format
quality-estimation-task.1.pdf	Published (author's copy) - Peer Reviewed	213.37 kB	Adobe PDF	View/Open

This item is protected by original copyright

View License

Please note: There is a known bug in some browsers that causes an error when a user tries to view large pdf file within the browser window. If you receive the message "The file is damaged and could not be repaired", please try one of the solutions linked below based on the browser you are using.