2021 Fiscal Year Final Research Report
Argument-based Bayesian generative models for argumentation mining
| Project/Area Number |
18K11428
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61030:Intelligent informatics-related
|
|---|
| Research Institution | The University of Electro-Communications |
|---|
Principal Investigator |
Kido Hiroyuki 電気通信大学, 大学院情報理工学研究科, 客員研究員 (90705287)
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Keywords | 抽象的議論 / 非単調論理 / ベイズ統計 / 逆問題 |
|---|
| Outline of Final Research Achievements |
Argument mining aims to extract an argumentative structure from texts written or spoken in natural languages. The key idea we studied in this project is an inverse problem of abstract argumentation studied in formal logic. The main contributions of this project include a probabilistic model of the idea and its effective use in argumentation mining. The research achievements of this project have been presented at a peer-reviewed conference and workshop and published in arXiv.
|
| Free Research Field |
人工知能
|
| Academic Significance and Societal Importance of the Research Achievements |
既存のほとんどの研究は抽象的議論の順問題に相当する．我々の与えた確率モデルは逆問題への一般的な解法を与えるだけでなく，順問題および順問題と逆問題の連結である複合問題への一般的な解法を与える．また，この逆問題の着想は本研究課題が対象とした形式的議論だけでなく，形式的論理も適用すべきことがわかった．
|
