Structuralizing and aggregating instances of abstract world knowledge
| Project/Area Number |
16H06614
|
|---|
| Research Category |
Grant-in-Aid for Research Activity Start-up
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Tohoku University |
|---|
Principal Investigator |
Inoue Naoya 東北大学, 情報科学研究科, 助教 (80778605)
|
|---|
| Project Period (FY) |
2016-08-26 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2016: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 世界知識 / 自然言語処理 / 推論 / 人工知能 / 談話解析 / 常識推論 / 論述構造解析 / 知識獲得 / 論理推論 / 知識構造化 / ディベート理解 |
|---|
| Outline of Final Research Achievements |
We have studied core technologies for automatically acquiring world knowledge which makes artificial intelligence smarter, such as causality, from large-scale textual data. We also studied an abductive reasoner which predicts a new hypothesis based on observed facts and world knowledge. Focusing on argumentative texts under such topics as "Should we invest in space exploration?", we developed a computational model to identify the relationship between a claim and premise. We also developed a framework that can perform flexible reasoning by leveraging distributed representations.
|
Report
(3 results)
Research Products
(12 results)
-
-
-
[Journal Article] An RNN-based Binary Classifier for the Story Cloze Test2017
Author(s)
Melissa Roemmele, Sosuke Kobayashi, Naoya Inoue and Andrew Gordon
-
Journal Title
Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics
Volume: －
Pages: 74-78
Related Report
Peer Reviewed / Open Access / Int'l Joint Research / Acknowledgement Compliant
-
-
-
-
-
-
-
-
-
