# Multimodal Logical Inference System for Visual-Textual Entailment

arXiv: https://arxiv.org/abs/1906.03952 · HTML: https://mlsanity.com/paper/1906.03952/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2019.

## Built on by (most cited first, 11 of 11)

- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [MultiViz: Towards Visualizing and Understanding Multimodal Models](https://mlsanity.com/paper/2207.00056/) (2022)
- [TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning](https://mlsanity.com/paper/2402.19467/) (2024)
- [AlignVE: Visual Entailment Recognition Based on Alignment Relations](https://mlsanity.com/paper/2211.08736/) (2022)
- [MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization](https://mlsanity.com/paper/2510.01659/) (2025)
- [A Survey on Interpretable Cross-modal Reasoning](https://mlsanity.com/paper/2309.01955/) (2023)
- [Video-VoT-R1: An efficient video inference model integrating image packing and AoE architecture](https://mlsanity.com/paper/2503.15807/) (2025)
- [Foundations of Multisensory Artificial Intelligence](https://mlsanity.com/paper/2404.18976/) (2024)
- [Building a Video-and-Language Dataset with Human Actions for Multimodal Logical Inference](https://mlsanity.com/paper/2106.14137/) (2021)
- [Logical Inference for Counting on Semi-structured Tables](https://mlsanity.com/paper/2204.07803/) (2022)
- [Don't Learn, Ground: A Case for Natural Language Inference with Visual Grounding](https://mlsanity.com/paper/2511.17358/) (2025)

## Abstract (arXiv)

A large amount of research about multimodal inference across text and vision has been recently developed to obtain visually grounded word and sentence representations. In this paper, we use logic-based representations as unified meaning representations for texts and images and present an unsupervised multimodal logical inference system that can effectively prove entailment relations between them. We show that by combining semantic parsing and theorem proving, the system can handle semantically complex sentences for visual-textual inference.