DisCoCLIP: A Distributional Compositional Tensor Network Encoder for Vision-Language Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911176229650432 |
|---|---|
| author | Lo, Kin Ian Hawashin, Hala Abbaszadeh, Mina Limback-Stokin, Tilen Wazni, Hadi Sadrzadeh, Mehrnoosh |
| author_facet | Lo, Kin Ian Hawashin, Hala Abbaszadeh, Mina Limback-Stokin, Tilen Wazni, Hadi Sadrzadeh, Mehrnoosh |
| contents | Recent vision-language models excel at large-scale image-text alignment but often neglect the compositional structure of language, leading to failures on tasks that hinge on word order and predicate-argument structure. We introduce DisCoCLIP, a multimodal encoder that combines a frozen CLIP vision transformer with a novel tensor network text encoder that explicitly encodes syntactic structure. Sentences are parsed with a Combinatory Categorial Grammar parser to yield distributional word tensors whose contractions mirror the sentence's grammatical derivation. To keep the model efficient, high-order tensors are factorized with tensor decompositions, reducing parameter count from tens of millions to under one million. Trained end-to-end with a self-supervised contrastive loss, DisCoCLIP markedly improves sensitivity to verb semantics and word order: it raises CLIP's SVO-Probes verb accuracy from 77.6% to 82.4%, boosts ARO attribution and relation scores by over 9% and 4%, and achieves 93.7% on a newly introduced SVO-Swap benchmark. These results demonstrate that embedding explicit linguistic structure via tensor networks yields interpretable, parameter-efficient representations that substantially improve compositional reasoning in vision-language tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21287 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DisCoCLIP: A Distributional Compositional Tensor Network Encoder for Vision-Language Understanding Lo, Kin Ian Hawashin, Hala Abbaszadeh, Mina Limback-Stokin, Tilen Wazni, Hadi Sadrzadeh, Mehrnoosh Computation and Language Artificial Intelligence Recent vision-language models excel at large-scale image-text alignment but often neglect the compositional structure of language, leading to failures on tasks that hinge on word order and predicate-argument structure. We introduce DisCoCLIP, a multimodal encoder that combines a frozen CLIP vision transformer with a novel tensor network text encoder that explicitly encodes syntactic structure. Sentences are parsed with a Combinatory Categorial Grammar parser to yield distributional word tensors whose contractions mirror the sentence's grammatical derivation. To keep the model efficient, high-order tensors are factorized with tensor decompositions, reducing parameter count from tens of millions to under one million. Trained end-to-end with a self-supervised contrastive loss, DisCoCLIP markedly improves sensitivity to verb semantics and word order: it raises CLIP's SVO-Probes verb accuracy from 77.6% to 82.4%, boosts ARO attribution and relation scores by over 9% and 4%, and achieves 93.7% on a newly introduced SVO-Swap benchmark. These results demonstrate that embedding explicit linguistic structure via tensor networks yields interpretable, parameter-efficient representations that substantially improve compositional reasoning in vision-language tasks. |
| title | DisCoCLIP: A Distributional Compositional Tensor Network Encoder for Vision-Language Understanding |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.21287 |