KIT | KIT-Bibliothek | Impressum
Open Access Logo
§
Volltext
URN: urn:nbn:de:swb:90-421292

Adaptation in Machine Translation

Niehues, Jan

Abstract:
Statistical machine translation (SMT) has emerged as the currently most promising approach for machine translation. One limitation to date, however, is that the quality of SMT systems strongly depends on the similarity between the training data and its deployment. This thesis is devoted to adapting MT systems in the scenario of mismatching training data. We develop different approaches to increase performance even though all or some of the training data does not match the system's application.


Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Hochschulschrift
Jahr 2014
Sprache Englisch
Identifikator KITopen ID: 1000042129
Verlag Karlsruhe
Abschlussart Dissertation
Fakultät Fakultät für Informatik (INFORMATIK)
Institut Institut für Anthropomatik und Robotik (IAR)
Prüfungsdaten 17.01.2014
Referent/Betreuer Prof. A. Waibel
Schlagworte Statistical Machine Translation, Domain Adaptation, Neural Network, Mismatching Data
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft KITopen Landing Page