Papers by Jonas Klaff
Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing research on predicting argument quality based on subjective assessments of human annotators ignores this limitation. |
| Approach: | They propose to compare different revisions of the same claim to assess their quality . they use logistic regression and transformer-based neural networks to learn quality indicators . |
| Outcome: | The proposed tasks show that the learned indicators generalize well across topics. |