Carregant...
Carregant...

Vés al contingut (premeu Retorn)

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

Autor
Labaka, G.; Sarasola, K.; Díaz de Ilarraza, A.; España-Bonet, C.; Marquez, L.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
International Workshop on Using Linguistic Information for Hybrid Machine Translation
Any de l'edició
2011
Data de presentació
2011-11-18
Llibre d'actes
LIHMT 2011 Sponsors International Workshop on Using Linguistic Information for Hybrid Machine Translation
Pàgina inicial
50
Pàgina final
57
Repositori
http://hdl.handle.net/2117/17063 Obrir en finestra nova
URL
http://ixa2.si.ehu.es/lihmt2011/proceedings.pdf Obrir en finestra nova
Resum
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...
Citació
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.
Grup de recerca
GPLN - Grup de Processament del Llenguatge Natural

Participants

  • Labaka, Gorka  (autor ponent)
  • Sarasola, Kepa  (autor ponent)
  • Díaz de Ilarraza Sánchez, Arantza  (autor ponent)
  • España Bonet, Cristina  (autor ponent)
  • Màrquez Villodre, Lluís  (autor ponent)

Arxius