Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.11197 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914801975820288 |
|---|---|
| author | Creanga, Claudiu Dinu, Liviu P. |
| author_facet | Creanga, Claudiu Dinu, Liviu P. |
| contents | Natural Language Inference (NLI) is foundational for evaluating language understanding in AI. However, progress has plateaued, with models failing on ambiguous examples and exhibiting poor generalization. We argue that this stems from disregarding the subjective nature of meaning, which is intrinsically tied to an individual's \textit{weltanschauung} (which roughly translates to worldview). Existing NLP datasets often obscure this by aggregating labels or filtering out disagreement. We propose a perspectivist approach: building datasets that capture annotator demographics, values, and justifications for their labels. Such datasets would explicitly model diverse worldviews. Our initial experiments with a subset of the SBIC dataset demonstrate that even limited annotator metadata can improve model performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_11197 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Designing NLP Systems That Adapt to Diverse Worldviews Creanga, Claudiu Dinu, Liviu P. Computation and Language Natural Language Inference (NLI) is foundational for evaluating language understanding in AI. However, progress has plateaued, with models failing on ambiguous examples and exhibiting poor generalization. We argue that this stems from disregarding the subjective nature of meaning, which is intrinsically tied to an individual's \textit{weltanschauung} (which roughly translates to worldview). Existing NLP datasets often obscure this by aggregating labels or filtering out disagreement. We propose a perspectivist approach: building datasets that capture annotator demographics, values, and justifications for their labels. Such datasets would explicitly model diverse worldviews. Our initial experiments with a subset of the SBIC dataset demonstrate that even limited annotator metadata can improve model performance. |
| title | Designing NLP Systems That Adapt to Diverse Worldviews |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.11197 |