ACL Findings2021
Probing Image-Language Transformers for Verb Understanding
Lisa Anne Hendricks, Aida Nematzadeh
Abstract
Multimodal image-language transformers have achieved impressive results on a variety of tasks that rely on fine-tuning (e.g., visual question answering and image retrieval). We are interested in shedding light on the quality of their pretrained representationsin particular, if these models can distinguish different types of verbs or if they rely solely on nouns in a given sentence. To do so, we collect a dataset of image-sentence pairs (in English) consisting of 421 verbs that are either visual or commonly found in the pretraining data (i.e., the Conceptual Captions dataset). We use this dataset to evaluate pretrained image-language transformers and find that they fail more in situations that require verb understanding compared to other parts of speech. We also investigate what category of verbs are particularly challenging.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
54 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers54
- Winoground: Probing Vision and Language Models for Visio-Linguistic CompositionalityTristan Thrush, Ryan Jiang, Max Bartolo, Amanpreet Singh et al.CVPR 2022 · 179 citations
- VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic PhenomenaLetitia Parcalabescu, Michele Cafagna, Lilitta Muradjan, Anette Frank et al.ACL 2022 · 147 citations
- CLIP-Event: Connecting Text and Images with Event StructuresManling Li, Ruochen Xu, Shuohang Wang, Luowei Zhou et al.CVPR 2022 · 103 citations
- Verbs in Action: Improving verb understanding in video-language modelsLiliane Momeni, Mathilde Caron, Arsha Nagrani, Andrew Zisserman et al.ICCV 2023 · 93 citations
- What the DAAM: Interpreting Stable Diffusion Using Cross AttentionRaphael Tang, Linqing Liu, Akshat Pandey, Zhiying Jiang et al.ACL 2023 · 93 citations
Related papers
- VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsWeijie Su, Xizhou Zhu, Yue Cao, Bin Li et al.ICLR 2020 · 1,825 citations
- Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsSoravit Changpinyo, Piyush Sharma, Nan Ding, Radu SoricutCVPR 2021
- 12-in-1: Multi-Task Vision and Language Representation LearningJiasen Lu, Vedanuj Goswami, Marcus Rohrbach, Devi Parikh et al.CVPR 2020
- Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?Mitja Nikolaus, Emmanuelle Salin, Stéphane Ayache, Abdellah Fourtassi et al.EMNLP 2022 · 5 citations
- Does Vision-and-Language Pretraining Improve Lexical Grounding?Tian Yun, Chen Sun, Ellie PavlickEMNLP Findings 2021 · 22 citations
