Efficient and accurate natural language analysis with lookahead of analysis actions
| Project/Area Number |
23700162
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2011 – 2012
|
| Project Status |
Completed (Fiscal Year 2012)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2012: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2011: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | 自然言語処理 / 機械学習 / 品詞タグ付け / 固有表現認識 / 構文解析 / 探索 / アルゴリズム / 評価関数 / チャンキング / 係り受け解析 |
|---|
| Research Abstract |
We have developed a novel machine learning algorithm that can be used for various natural language processing tasks such as part-of-speech tagging and parsing. The algorithm enables us to incorporate a look-ahead mechanism into a history-based model and significantly improve its accuracy. Experimental results demonstrate that our approach outperforms conditional random field models, which are currently the standard approach in the field, in several natural language processing tasks.
|
Report
(3 results)
Research Products
(6 results)
