| Project/Area Number |
25730136
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Nara Institute of Science and Technology |
|---|
Principal Investigator |
Neubig Graham 奈良先端科学技術大学院大学, 情報科学研究科, 助教 (70633428)
|
|---|
| Project Period (FY) |
2013-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2015: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2013: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 機械翻訳 / 訳選択 / 機械学習 / 構文情報 / 統計翻訳 / 構文解析 / 誤り分析 / 自然言語処理 / 評価尺度 |
|---|
| Outline of Final Research Achievements |
One of the reasons for the recent progress in the field of machine translation is the rise of statistical machine translation (SMT), which automatically learns translation rules from translated data. However, SMT does not directly consider the reason why it chooses a particular translation, and thus has a tendency not made by rule-based machine translation systems. In this work, we developed methods to automatically learn rules about why a machine translation system should choose a particular translation, and introduce them into SMT systems. Specifically, we developed a translation system based on linguistic knowledge, introduced reasons for translation into this system, created a method to efficiently analyze its output, and developed methods to learn the rules for translation from multilingual data.
|
