Joint Natural Language Processing with Global Information
Project/Area Number |
23240020
|
Research Category |
Grant-in-Aid for Scientific Research (A)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Intelligent informatics
|
Research Institution | Nara Institute of Science and Technology |
Principal Investigator |
MATSUMOTO Yuji 奈良先端科学技術大学院大学, 情報科学研究科, 教授 (10211575)
|
Co-Investigator(Kenkyū-buntansha) |
SHIMBO Masashi 奈良先端科学技術大学院大学, 情報科学研究科, 准教授 (90311589)
DUH Kevin 奈良先端科学技術大学院大学, 情報科学研究科, 助教 (80637322)
KOMACHI Mamoru 首都大学東京, システムデザイン研究科, 准教授 (60581329)
浅原 正幸 奈良先端科学技術大学院大学, 情報科学研究科, 助教 (80379528)
|
Project Period (FY) |
2011-04-01 – 2014-03-31
|
Project Status |
Completed (Fiscal Year 2013)
|
Budget Amount *help |
¥38,480,000 (Direct Cost: ¥29,600,000、Indirect Cost: ¥8,880,000)
Fiscal Year 2013: ¥12,220,000 (Direct Cost: ¥9,400,000、Indirect Cost: ¥2,820,000)
Fiscal Year 2012: ¥13,130,000 (Direct Cost: ¥10,100,000、Indirect Cost: ¥3,030,000)
Fiscal Year 2011: ¥13,130,000 (Direct Cost: ¥10,100,000、Indirect Cost: ¥3,030,000)
|
Keywords | 自然言語処理 / 機械学習 / 形態素解析 / 統語解析 / 述語項構造解析 / 同時処理 / 大域情報 / 言語資源 |
Research Abstract |
We investigated the usage of global information for joint processing of natural language processing such as word segmentation, part-of-speech tagging, parsing and predicate argument structure analysis. For English, we collected multi-word expressions that act as functional words and implemented part-of-speech tagging and syntactic analysis using them. We also proposed various syntactic processing methods, one that utilizes both top-down and bottom-up information jointly and another that keeps multiple candidates in the form of parse forest and uses re-ranking algorithm to select the best answer. For predicate argument structure analysis, we proposed a method that utilizes various types of features in a joint framework and another method that used Markov Logic Networks to incorporate various constraints jointly.
|
Report
(4 results)
Research Products
(36 results)