KIT | KIT-Bibliothek | Impressum | Datenschutz

Multilingual Neural Translation

Ha, Thanh-Le

Abstract (englisch):

Machine translation (MT) refers to the technology that can automatically translate contents in one language into other languages. Being an important research area in the field of natural language processing, machine translation has typically been considered one of most challenging yet exciting problems. Thanks to research progress in the data-driven statistical machine translation (SMT), MT is recently capable of providing adequate translation services in many language directions and it has been widely deployed in various practical applications and scenarios.

Nevertheless, there exist several drawbacks in the SMT framework. The major drawbacks of SMT lie in its dependency in separate components, its simple modeling approach, and the ignorance of global context in the translation process. Those inherent drawbacks prevent the over-tuned SMT models to gain any noticeable improvements over its horizon. Furthermore, SMT is unable to formulate a multilingual approach in which more than two languages are involved. The typical workaround is to develop multiple pair-wise SMT systems and connect them in a complex bundle to perform multilingual translation. ... mehr


Volltext §
DOI: 10.5445/IR/1000104498
Veröffentlicht am 03.02.2020
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Hochschulschrift
Publikationsjahr 2020
Sprache Englisch
Identifikator KITopen-ID: 1000104498
Verlag Karlsruher Institut für Technologie (KIT)
Umfang XXI, 110 S.
Art der Arbeit Dissertation
Fakultät Fakultät für Informatik (INFORMATIK)
Institut Institut für Anthropomatik und Robotik (IAR)
Prüfungsdatum 09.01.2019
Referent/Betreuer Waibel, A.
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page