Matches in ScholarlyData for { <https://w3id.org/scholarlydata/inproceedings/lrec2008/papers/780> ?p ?o. }
Showing items 1 to 16 of
16
with 100 items per page.
- 780 creator akira-terada.
- 780 creator eiko-yamamoto.
- 780 creator hitoshi-isahara.
- 780 creator masao-utiyama.
- 780 creator yasunori-abe.
- 780 type InProceedings.
- 780 label "Application of Resource-based Machine Translation to Real Business Scenes".
- 780 sameAs 780.
- 780 abstract "As huge quantities of documents have become available, services using natural language processing technologies trained by huge corpora have emerged, such as information retrieval and information extraction. In this paper we verify the usefulness of resource-based, or corpus-based, translation in the aviation domain as a real business situation. This study is important from both a business perspective and an academic perspective. Intuitively, manuals for similar products, or manuals for different versions of the same product, are likely to resemble each other. Therefore, even with only a small training data, a corpus-based MT system can output useful translations. The corpus-based approach is powerful when the target is repetitive. Manuals for similar products, or manuals for different versions of the same product, are real-world documents that are repetitive. Our experiments on translation of manual documents are still in a beginning stage. However, the BLEU score from very small number of training sentences is already rather high. We believe corpus-based machine translation is a player full of promise in this kind of actual business scene.".
- 780 hasAuthorList authorList.
- 780 hasTopic Linguistics.
- 780 isPartOf proceedings.
- 780 keyword "Machine Translation, SpeechToSpeech Translation".
- 780 keyword "Multilinguality".
- 780 keyword "Usability, user satisfaction".
- 780 title "Application of Resource-based Machine Translation to Real Business Scenes".