BERTScoreVisualizer: A Web Tool for Understanding Simplified Text Evaluation with BERTScore
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912046512078848 |
|---|---|
| author | Jaskowski, Sebastian Chava, Sahasra Shah, Agam |
| author_facet | Jaskowski, Sebastian Chava, Sahasra Shah, Agam |
| contents | The BERTScore metric is commonly used to evaluate automatic text simplification systems. However, current implementations of the metric fail to provide complete visibility into all information the metric can produce. Notably, the specific token matchings can be incredibly useful in generating clause-level insight into the quality of simplified text. We address this by introducing BERTScoreVisualizer, a web application that goes beyond reporting precision, recall, and F1 score and provides a visualization of the matching between tokens. We believe that our software can help improve the analysis of text simplification systems by specifically showing where generated, simplified text deviates from reference text. We host our code and demo on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17160 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BERTScoreVisualizer: A Web Tool for Understanding Simplified Text Evaluation with BERTScore Jaskowski, Sebastian Chava, Sahasra Shah, Agam Computation and Language The BERTScore metric is commonly used to evaluate automatic text simplification systems. However, current implementations of the metric fail to provide complete visibility into all information the metric can produce. Notably, the specific token matchings can be incredibly useful in generating clause-level insight into the quality of simplified text. We address this by introducing BERTScoreVisualizer, a web application that goes beyond reporting precision, recall, and F1 score and provides a visualization of the matching between tokens. We believe that our software can help improve the analysis of text simplification systems by specifically showing where generated, simplified text deviates from reference text. We host our code and demo on GitHub. |
| title | BERTScoreVisualizer: A Web Tool for Understanding Simplified Text Evaluation with BERTScore |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.17160 |