Hybrid Architectures for Machine Translation Systems.
Although some progress has been made on the quality of Machine Translation in recent years, there is still a significant potential for quality improvement. There has also been a shift in paradigm of machine translation, from “classical” rule-based systems like METAL or LMT towards example-based or s...
| Publicado en: | Language Resources & Evaluation Vol. 39; no. 1; pp. 91 - 109 |
|---|---|
| Autor principal: | |
| Formato: | Artículo |
| Publicado: |
Springer Nature
Feb2005
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=19148543&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 19148543 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 1574020X 179V jtl: Language Resources & Evaluation issn: 1574020X maglogo: N pubinfo: dt: Feb2005 vid: 39 iid: 1 pid: 237 pub: Springer Nature artinfo: ui: 19148543 10.1007/s10579-005-2698-z ppf: 91 ppct: 18 formats: fmt: @attributes: type: P size: 256KB tig: atl: Hybrid Architectures for Machine Translation Systems. aug: au: Thurmair, Gregor affil: linguatic GmbH, Gottfried Keller Strrasse 12 81245 Munich Germany su: Translators (Computer programs) Translating & interpreting Language & languages Computer software Computer architecture sug: subj: Translators (Computer programs) Translating & interpreting Language & languages Computer software Computer architecture keyword: evaluation architecture Machine Translation MT architecture ab: Although some progress has been made on the quality of Machine Translation in recent years, there is still a significant potential for quality improvement. There has also been a shift in paradigm of machine translation, from “classical” rule-based systems like METAL or LMT towards example-based or statistical MT. It seems to be time now to evaluate the progress and compare the results of these efforts, and draw conclusions for further improvements of MT quality. The paper starts with a comparison between statistical MT (henceforth: SMT) and rule-based MT (henceforth: RMT) systems, and describes the set-up and the evaluation results; the second section analyses the strengths and weaknesses of the respective approaches, and the third one discusses models of an architecture for a hybrid system. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Language Resources & Evaluation is a copyright of Springer, 2005. All Rights Reserved. item: Language Resources & Evaluation holder: Springer Nature dt: @attributes: year: 2005 holdings: @attributes: islocal: N |
|---|