Development of incremental dependency parsing techniques for spoken language applications
| Project/Area Number |
25730134
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Nagoya University |
|---|
Principal Investigator |
Ohno Tomohiro 名古屋大学, 情報基盤センター, 助教 (20402472)
|
|---|
| 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: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2014: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2013: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 依存構造解析 / 漸進的処理 / 構文解析 / 話し言葉処理 / 字幕生成 / リアルタイム処理 / 入力予測 / 語順整序 / 改行挿入 |
|---|
| Outline of Final Research Achievements |
In this research, we developed a new incremental dependency parser which is necessary for a spoken language application such as simultaneous interpretation and real-time captioning. Our parser identifies not only dependencies between inputted bunsetsus but also independencies between bunsetsus of which the modified bunsetsu has not been inputted and any other inputted bunsetsus, whenever a bunsetsu is inputted. In addition, if there are two or more bunsetsus of which the modified bunsetsu has not been inputted, our parser detects whether or not those bunsetsus depend on a same non-inputted bunsetsu. Next, to improve the performance of an incremental dependency parser, we constructed a large-scale dataset which expresses a process of human language processing, and revealed parts of human capacities and behaviors on incremental dependency parsing. Furthermore, we developed a method which can concurrently execute dependency parsing and word reordering.
|
Report
(4 results)
Research Products
(11 results)
