Multi-Domain Adapted Machine Translation Using Unsupervised Text Clustering
Chapter
Accepted version
Permanent lenke
http://hdl.handle.net/11250/2391293Utgivelsesdato
2015Metadata
Vis full innførselSamlinger
Originalversjon
Christiansen, Henning; Stojanovic, Isidora; Papadopoulos, George A. [Eds.] Modeling and Using Context: 9th International and Interdisciplinary Conference, CONTEXT 2015, Larnaca, Cyprus, November 2-6, 2015. Proceedings p. 201-213 Lecture Notes in Computer Science, Springer Science+Business Media B.V., 2015 10.1007/978-3-319-25591-0_15Sammendrag
Domain Adaptation in Machine Translation means to take a machine translation system that is restricted to work in a specific context and to enable the system to translate text from a different domain. The paper presents a two-step domain adaptation strategy, by first making use of unlabeled training material through an unsupervised algorithm, the Self-Organizing Map, to create auxiliary language models, and then to include these models dynamically in a machine translation pipeline