Papers by Timon Gurcke
Belief-based Generation of Argumentative Claims (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods to generate argument with the ability to encode beliefs are limited by the noise generated by the automatic collection of bag-of-words. |
| Approach: | They propose to augment argument generation technology with ability to encode beliefs . they model users' beliefs via their stances on big issues and extend text generation models with extra input reflecting user's beliefs. |
| Outcome: | The proposed approach is low in effectiveness because of the noise produced by the automatic collection of bag-of-words. |
The Moral Debater: A Study on the Computational Generation of Morally Framed Arguments (2022.acl-long)
Copied to clipboard
| Challenge: | Existing arguments that focus on shared values are based on prior beliefs and morals, but little research has been done on the effectiveness of these proxies. |
| Approach: | They propose a system that automatically generates arguments focusing on different morals and ask liberals and conservatives to evaluate the impact of these arguments. |
| Outcome: | The proposed system generates arguments focusing on different morals, and the results are compared with existing arguments. |