- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Knowledge Graph Search feature is available on CiNii Labs
- 【Updated on June 30, 2025】Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Imposing Constraints from the Source Tree on ITG Constraints for SMT
-
- YAMAMOTO Hirofumi
- School of Science and Engineering, Dept. Informatics, Kinki University National Institute of Communications Technology, and with ATR Spoken Language Translation Research Laboratories
-
- OKUMA Hideo
- National Institute of Communications Technology, and with ATR Spoken Language Translation Research Laboratories
-
- SUMITA Eiichiro
- National Institute of Communications Technology, and with ATR Spoken Language Translation Research Laboratories
Search this article
Description
In the current statistical machine translation (SMT), erroneous word reordering is one of the most serious problems. To resolve this problem, many word-reordering constraint techniques have been proposed. Inversion transduction grammar (ITG) is one of these constraints. In ITG constraints, target-side word order is obtained by rotating nodes of the source-side binary tree. In these node rotations, the source binary tree instance is not considered. Therefore, stronger constraints for word reordering can be obtained by imposing further constraints derived from the source tree on the ITG constraints. For example, for the source word sequence { a b c d }, ITG constraints allow a total of twenty-two target word orderings. However, when the source binary tree instance ((a b) (c d)) is given, our proposed “imposing source tree on ITG” (IST-ITG) constraints allow only eight word orderings. The reduction in the number of word-order permutations by our proposed stronger constraints efficiently suppresses erroneous word orderings. In our experiments with IST-ITG using the NIST MT08 English-to-Chinese translation track's data, the proposed method resulted in a 1.8-points improvement in character BLEU-4 (35.2 to 37.0) and a 6.2% lower CER (74.1 to 67.9%) compared with our baseline condition.
Journal
-
- IEICE Transactions on Information and Systems
-
IEICE Transactions on Information and Systems E92-D (9), 1762-1770, 2009
The Institute of Electronics, Information and Communication Engineers
- Tweet
Details 詳細情報について
-
- CRID
- 1390282679355492736
-
- NII Article ID
- 10026811036
-
- NII Book ID
- AA10826272
-
- ISSN
- 17451361
- 09168532
-
- Text Lang
- en
-
- Article Type
- journal article
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
- KAKEN
- OpenAIRE
-
- Abstract License Flag
- Disallowed