Compound Processing for Phrase-Based Statistical Machine Translation

Compound Processing for Phrase-Based Statistical Machine Translation

In this thesis I explore how compound processing can be used to improve phrase-based statistical machine translation (PBSMT) between English and German/Swedish. Both German and Swedish generally use closed compounds, which are written as one word without spaces or other indicators of word boundaries...

Full description

Bibliographic Details
Main Author: Stymne, Sara
Format: Others
Language:English
Published: Linköpings universitet, NLPLAB - Laboratoriet för databehandling av naturligt språk 2009
Subjects:
Machine translation
compounds
factored translation
statistical machine translation
computational linguistics
Language Technology (Computational Linguistics)
Språkteknologi (språkvetenskaplig databehandling)
Computer Sciences
Datavetenskap (datalogi)
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-51416
http://nbn-resolving.de/urn:isbn:9789173935012

Internet

http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-51416
http://nbn-resolving.de/urn:isbn:9789173935012

Similar Items