Probabilistic Formalization for Example-based Machine Translation
-
- ARAMAKI EIJI
- Department of Planning, Information and Management, University of Tokyo Hospital
-
- KUROHASHI SADAO
- Graduate School of Informatics, Kyoto University
-
- KASHIOKA HIDEKI
- National Institute of Information and Communications Technology ATR Spoken Language Translation Research Laboratories
-
- KATO NAOTO
- Science and Technical Research Laboratories of NHK
Bibliographic Information
- Other Title
-
- 用例ベース翻訳の確率的モデル化
- ヨウレイ ベース ホンヤク ノ カクリツテキ モデルカ
Search this article
Abstract
Example-based machine translation (EBMT) systems, so far, rely on heuristic measures in retrieving translation examples.Such a heuristic measure costs time to adjust, and might make its algorithm unclear.This paper presents a probabilistic model for EBMT.Under the proposed model, the system searches the translation example combination which has the highest probability.The proposed model clearly formalizes EBMT process.In addition, the model can naturally incorporate the context similarity of translation examples.The experimental results demonstrate that the proposed model has a slightly better translation quality than state-of-the-art EBMT systems.
Journal
-
- Journal of Natural Language Processing
-
Journal of Natural Language Processing 13 (3), 3-19, 2006
The Association for Natural Language Processing
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282679452743552
-
- NII Article ID
- 130004291884
- 10018202687
- 10018468379
-
- NII Book ID
- AN10472659
-
- ISSN
- 21858314
- 13407619
-
- HANDLE
- 2261/29114
-
- NDL BIB ID
- 8048712
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- IRDB
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed