Matches in ScholarlyData for { <https://w3id.org/scholarlydata/inproceedings/lrec2008/papers/733> ?p ?o. }
Showing items 1 to 14 of
14
with 100 items per page.
- 733 creator andreas-eisele.
- 733 creator martin-kay.
- 733 creator yu-chen.
- 733 type InProceedings.
- 733 label "Improving Statistical Machine Translation Efficiency by Triangulation".
- 733 sameAs 733.
- 733 abstract "In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model that enlarges the search space for the decoder, and consequently requires more time and more resources to translate. This paper describes an attempt to reduce the model size by filtering out the less probable entries based on testing correlation using additional training data in an intermediate third language. The central idea behind the approach is triangulation, the process of incorporating multilingual knowledge in a single system, which eventually utilizes parallel corpora available in more than two languages. We conducted experiments using Europarl corpus to evaluate our approach. The reduction of the model size can be up to 70% while the translation quality is being preserved.".
- 733 hasAuthorList authorList.
- 733 hasTopic Linguistics.
- 733 isPartOf proceedings.
- 733 keyword "Machine Translation, SpeechToSpeech Translation".
- 733 keyword "Multilinguality".
- 733 keyword "Statistical methods".
- 733 title "Improving Statistical Machine Translation Efficiency by Triangulation".