Challenge: Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora.
Approach: They propose to utilize visual content for disambiguation and promoting latent space alignment in unsupervised machine translation by using multimodal back-translation and pseudo visual pivoting.
Outcome: The proposed model improves over state-of-the-art methods and generalizes well when images are not available at the testing time.

Similar Papers

Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation (2021.acl-long)

Copied to clipboard

Challenge: Recent studies report improvements when equipping models with multimodal information, but it remains unclear whether such improvements actually come from the multimodal part.
Approach: They propose to extend conventional text-only translation models with multimodal information by extending them with visual input.
Outcome: The proposed models replicate similar gains as recently developed multimodal-integrated systems achieved, but learn to ignore multimodal information.
Visual Pivoting Unsupervised Multimodal Machine Translation in Low-Resource Distant Language Pairs (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing studies show that neural MT achieves much worse translation quality than statistical MT with a small number of corpora.
Approach: They propose a visual pivoting method for alignment between distant language pairs . they first construct a dataset and then apply it to pre-training and fine-tuning .
Outcome: The proposed method outperforms baselines on DLPs and close language pairs.
Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation (2023.acl-long)

Copied to clipboard

Challenge: Recent work in multimodal machine translation (MT) has shown that ambiguity can be resolved using accompanying context such as images.
Approach: They propose a multimodal machine translation approach based on a strong text-only MT model and a novel guided self-attention mechanism to train it.
Outcome: The proposed model outperforms existing models on EnglishFrench, EnglishGerman and EnglishCzech benchmarks and is freely available.
Neural Machine Translation with Phrase-Level Universal Visual Representations (2022.acl-long)

Copied to clipboard

Challenge: Existing multimodal machine translation methods require paired input of source sentence and image, which makes them suffer from shortage of sentence-image pairs.
Approach: They propose a phrase-level retrieval-based method to get visual information from existing sentence-image data sets.
Outcome: The proposed method significantly outperforms strong baselines on multiple MMT datasets, especially when the textual context is limited.
Towards Zero-Shot Multimodal Machine Translation (2025.findings-naacl)

Copied to clipboard

Challenge: Current multimodal machine translation systems rely on fully supervised data, which is costly to collect and prevents extension of MMT to language pairs with no such data.
Approach: They propose a method to bypass the need for fully supervised data to train MMT systems . they adapt a strong text-only machine translation model to a visually conditioned language model and a divergence test set to evaluate how well models use images to disambiguate translations.
Outcome: The proposed method can generalize to languages with no fully supervised training data.
Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination (2023.acl-long)

Copied to clipboard

Challenge: Current neural machine translation (NMT) relies on parallel sentences, which obstructs the development of NMT for minor languages.
Approach: They propose an unsupervised multimodal machine translation setup where the model is trained with source-text image pairs and tested with only source- text inputs.
Outcome: The proposed model outperforms the baseline model on the task and setup, helping yield translations with better completeness, relevance and fluency without relying on paired images.
Multilingual-To-Multimodal (M2M): Unlocking New Languages with Monolingual Text (2026.findings-eacl)

Copied to clipboard

Challenge: Existing multimodal models rely on machine translation, but performance drops for other languages due to limited multilingual multimodal resources.
Approach: They propose a lightweight alignment method that learns only a few linear layers using English text alone to map multilingual text embeddings into multimodal space.
Outcome: M2M achieves strong zero-shot transfer on XTD Text-to-Image retrieval in English and spanish . it learns only a few linear layers to map multilingual text embeddings into multimodal space .
Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation (2025.acl-long)

Copied to clipboard

Challenge: Document Image Machine Translation (DIMT) faces generalization challenges due to limited training data and the complex interplay between visual and textual information.
Approach: They propose a single-to-mix Modality alignment framework leveraging Multimodal Large Language Models (MLLMs) this framework aligns an imageonly encoder with multimodal representations of an MLLM pre-trained on large-scale document image datasets.
Outcome: The proposed framework improves translation quality in cross-domain generalization and challenging document image scenarios.
A Visual Attention Grounding Neural Model for Multimodal Machine Translation (D18-1)

Copied to clipboard

Challenge: Existing approaches to multimodal machine translation do not integrate visual information into the translation process.
Approach: They propose a multimodal machine translation model that utilizes parallel visual and textual information.
Outcome: The proposed model outperforms existing methods on the Multi30K and Ambiguous COCO datasets.
Enabling Unsupervised Neural Machine Translation with Word-level Visual Representations (2023.findings-emnlp)

Copied to clipboard

Challenge: Unsupervised neural machine translation methods have been observed to make particular errors in comparison to supervised machine translation, such as confusing nouns that pertain to the same semantic category.
Approach: They propose a method that incorporates images at the word level to augment lexical mappings.
Outcome: Experiments on a multi-lingual dataset show that the proposed method generates more accurate translations with only monolingual data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations