Improvement of alignment for statistical and example-based machine translation and release of multilingual syntactic patterns
| Project/Area Number |
23500187
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Waseda University |
|---|
Principal Investigator |
LEPAGE Yves 早稲田大学, 理工学術院, 教授 (70573608)
|
|---|
| Project Period (FY) |
2011 – 2013
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2012: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2011: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 自然言語処理 / 機械翻訳 / 翻訳テーブル / アラインメント / 国際情報交換（オーストリア） / 国際情報交換（フランス） / Europarlコーパス / 単語アラインメント |
|---|
| Research Abstract |
Current machine translation systems rely on translation tables to translate. Translation tables look like usual dictionaries, but contain longer entries, with numerical values to assess the reliability of the entries. Translation tables are extracted automatically from translated texts by tools called subsentential aligners. In earlier research, we proposed a new subsentential aligner. It is simpler and faster than state-of-the-art tools. But it has lower quality scores in some translation tasks because its entries are not long enough. The goal of the project was to improve the tool so as to achieve as good results as the state-of-the-art tools. This has been achieved in various cases. Many of the translation tables output during the project have been made freely available to the community through a web site (all language pairs between the 11 languages on the common part of the Europarl corpus version 3).
|
Report
(4 results)
Research Products
(34 results)
