VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
Letitia Parcalabescu, Michele Cafagna, Lilitta Muradjan, Anette Frank, Iacer Calixto, Albert Gatt
Abstract
We propose VALSE (Vision And Language Structured Evaluation), a novel benchmark designed for testing general-purpose pretrained vision and language (V&L) models for their visio-linguistic grounding capabilities on specific linguistic phenomena. VALSE offers a suite of six tests covering various linguistic constructs. Solving these requires models to ground linguistic phenomena in the visual modality, allowing more fine-grained evaluations than hitherto possible. We build VALSE using methods that support the construction of valid foils, and report results from evaluating five widely-used V&L models. Our experiments suggest that current models have considerable difficulty addressing most phenomena. Hence, we expect VALSE to serve as an important benchmark to measure future progress of pretrained V&L models from a linguistic perspective, complementing the canonical task-centred V&L evaluations.- Anthology ID:
- 2022.acl-long.567
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8253–8280
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.567
- DOI:
- 10.18653/v1/2022.acl-long.567
- Cite (ACL):
- Letitia Parcalabescu, Michele Cafagna, Lilitta Muradjan, Anette Frank, Iacer Calixto, and Albert Gatt. 2022. VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8253–8280, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena (Parcalabescu et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2022.acl-long.567.pdf
- Code
- heidelberg-nlp/valse
- Data
- VALSE, MS COCO, VisDial, Visual Question Answering, Visual7W