|
Towards assessing natural language argument quality: results and open challenges| old_uid | 20063 |
|---|
| title | Towards assessing natural language argument quality: results and open challenges |
|---|
| start_date | 2022/02/24 |
|---|
| schedule | 13h30-14h30 |
|---|
| online | no |
|---|
| location_info | Amphithéâtre |
|---|
| details | Colloquium du Loria |
|---|
| summary | Argumentation is the process by which arguments are constructed and handled. Thus argumentation means that arguments are compared, evaluated in some respect and judged in order to establish whether any of them are warranted. The field of artificial argumentation is emerging as an important aspect of Artificial Intelligence research, in particular dealing with the automatic identification of argument structures in text. In this talk, I will focus on the issue of automatically assessing the quality of these identified natural language arguments. I will investigate the role of machine learning and reasoning methods to tackle this issue, focusing on the real world scenarios of political debates (with the assessment of fallacious arguments) and persuasive essays (for the scoring of students’ assays). |
|---|
| responsibles | Dutech |
|---|
| |
|