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.
BibTeX
@inproceedings{parcalabescu-etal-2022-valse,
title = "{VALSE}: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena",
author = "Parcalabescu, Letitia and
Cafagna, Michele and
Muradjan, Lilitta and
Frank, Anette and
Calixto, Iacer and
Gatt, Albert",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.567/",
doi = "10.18653/v1/2022.acl-long.567",
pages = "8253--8280"
}