Loading...
Loading...

Go to the content (press return)

Deep evaluation of hybrid architectures: simple metrics correlated with human judgments

Author
Labaka, G.; Sarasola, K.; Díaz de Ilarraza, A.; España-Bonet, C.; Marquez, L.
Type of activity
Presentation of work at congresses
Name of edition
International Workshop on Using Linguistic Information for Hybrid Machine Translation
Date of publication
2011
Presentation's date
2011-11-18
Book of congress proceedings
LIHMT 2011 Sponsors International Workshop on Using Linguistic Information for Hybrid Machine Translation
First page
50
Last page
57
Repository
http://hdl.handle.net/2117/17063 Open in new window
URL
http://ixa2.si.ehu.es/lihmt2011/proceedings.pdf Open in new window
Abstract
The process of developing hybrid MT systems is guided by the evaluation method used to compare different combinations of basic subsystems. This work presents a deep evaluation experiment of a hybrid architecture that tries to get the best of both worlds, rule-based and statistical. In a first evaluation human assessments were used to compare just the single statistical system and the hybrid one, the rule-based system was not compared by hand because the results of automatic evaluation showed a c...
Citation
Labaka, G. [et al.]. Deep evaluation of hybrid architectures: simple metrics correlated with human judgments. A: International Workshop on Using Linguistic Information for Hybrid Machine Translation. "LIHMT 2011 Sponsors International Workshop on Using Linguistic Information for Hybrid Machine Translation". Barcelona: 2011, p. 50-57.
Group of research
GPLN - Natural Language Processing Group

Participants

  • Labaka, Gorka  (author and speaker )
  • Sarasola, Kepa  (author and speaker )
  • Díaz de Ilarraza Sánchez, Arantza  (author and speaker )
  • España Bonet, Cristina  (author and speaker )
  • Màrquez Villodre, Lluís  (author and speaker )

Attachments