@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",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parcalabescu-etal-2022-valse">
<titleInfo>
<title>VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena</title>
</titleInfo>
<name type="personal">
<namePart type="given">Letitia</namePart>
<namePart type="family">Parcalabescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Cafagna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilitta</namePart>
<namePart type="family">Muradjan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anette</namePart>
<namePart type="family">Frank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iacer</namePart>
<namePart type="family">Calixto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Gatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">parcalabescu-etal-2022-valse</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.567</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.567</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>8253</start>
<end>8280</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
%A Parcalabescu, Letitia
%A Cafagna, Michele
%A Muradjan, Lilitta
%A Frank, Anette
%A Calixto, Iacer
%A Gatt, Albert
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F parcalabescu-etal-2022-valse
%X 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.
%R 10.18653/v1/2022.acl-long.567
%U https://aclanthology.org/2022.acl-long.567
%U https://doi.org/10.18653/v1/2022.acl-long.567
%P 8253-8280
Markdown (Informal)
[VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena](https://aclanthology.org/2022.acl-long.567) (Parcalabescu et al., ACL 2022)
ACL