Papers by Fabian Haak
ARTS: Assessing Readability & Text Simplicity (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing text simplification evaluation measures do not include simplicity labels on text level, as they are mainly based on a relational concept. |
| Approach: | They propose a method for language-independent construction of datasets for simplicity assessment using pairwise comparisons of texts in conjunction with an Elo algorithm to produce a simplicity ranking and simplicity scores. |
| Outcome: | The proposed method produces a ranking and simplicity scores for human-labeled and three GPT-labelled datasets. |
BATS: BenchmArking Text Simplicity 🦇 (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on text simplification focus on the difference between a source text and its simplified variant. |
| Approach: | They propose to use a dataset to assess the overall simplicity of text. |
| Outcome: | The proposed method compared 15 datasets on text simplification and their impact on the overall simplicity of text. |