Proceedings of the Workshop on Automatic procedures in MT evaluation

Gregor Thurmair, Khalid Choukri, Bente Maegaard (Editors)


Anthology ID:
2007.mtsummit-aptme
Month:
September 11
Year:
2007
Address:
Copenhagen, Denmark
Venue:
MTSummit
SIG:
Publisher:
URL:
https://aclanthology.org/2007.mtsummit-aptme
DOI:
Bib Export formats:
BibTeX

pdf bib
Proceedings of the Workshop on Automatic procedures in MT evaluation
Gregor Thurmair | Khalid Choukri | Bente Maegaard

bib
The place of automatic evaluation metrics in external quality models for machine translation
Andrei Popescu-Belis

bib
Evaluating evaluation – lessons from the WMT 2007 shared task
Philipp Koehn | Chris Callison-Burch


Investigating why BLEU penalizes non-statistical systems
Eduard Hovy


Linguistic resources in support of various evaluation metrics
Christopher Cieri | Stephanie Strassel | Meghan Lammie Glenn | Lauren Friedman


Experiences and conclusions from the CESTA evaluation project
Olivier Hamon


Automatic evaluation in MT system production
Gregor Thurmair


Sensitivity of automated models for MT evaluation: proximity-based vs. performance-based methods
Bogdan Babych | Anthony Hartley


MT evaluation & TC-STAR
Khalid Choukri | Olivier Hamon | Djamel Mostefa