WinoPron: Revisiting English Winogender Schemas for Consistency, Coverage, and Grammatical Case
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_ | 1866916424361967616 |
|---|---|
| author | Gautam, Vagrant Steuer, Julius Bingert, Eileen Johns, Ray Lauscher, Anne Klakow, Dietrich |
| author_facet | Gautam, Vagrant Steuer, Julius Bingert, Eileen Johns, Ray Lauscher, Anne Klakow, Dietrich |
| contents | While measuring bias and robustness in coreference resolution are important goals, such measurements are only as good as the tools we use to measure them. Winogender Schemas (Rudinger et al., 2018) are an influential dataset proposed to evaluate gender bias in coreference resolution, but a closer look reveals issues with the data that compromise its use for reliable evaluation, including treating different pronominal forms as equivalent, violations of template constraints, and typographical errors. We identify these issues and fix them, contributing a new dataset: WinoPron. Using WinoPron, we evaluate two state-of-the-art supervised coreference resolution systems, SpanBERT, and five sizes of FLAN-T5, and demonstrate that accusative pronouns are harder to resolve for all models. We also propose a new method to evaluate pronominal bias in coreference resolution that goes beyond the binary. With this method, we also show that bias characteristics vary not just across pronoun sets (e.g., he vs. she), but also across surface forms of those sets (e.g., him vs. his). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05653 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WinoPron: Revisiting English Winogender Schemas for Consistency, Coverage, and Grammatical Case Gautam, Vagrant Steuer, Julius Bingert, Eileen Johns, Ray Lauscher, Anne Klakow, Dietrich Computation and Language While measuring bias and robustness in coreference resolution are important goals, such measurements are only as good as the tools we use to measure them. Winogender Schemas (Rudinger et al., 2018) are an influential dataset proposed to evaluate gender bias in coreference resolution, but a closer look reveals issues with the data that compromise its use for reliable evaluation, including treating different pronominal forms as equivalent, violations of template constraints, and typographical errors. We identify these issues and fix them, contributing a new dataset: WinoPron. Using WinoPron, we evaluate two state-of-the-art supervised coreference resolution systems, SpanBERT, and five sizes of FLAN-T5, and demonstrate that accusative pronouns are harder to resolve for all models. We also propose a new method to evaluate pronominal bias in coreference resolution that goes beyond the binary. With this method, we also show that bias characteristics vary not just across pronoun sets (e.g., he vs. she), but also across surface forms of those sets (e.g., him vs. his). |
| title | WinoPron: Revisiting English Winogender Schemas for Consistency, Coverage, and Grammatical Case |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.05653 |