Challenge: Existing studies on multi-modal neural machine translation focus on visual information, but text and image may not match exactly, and visual noise is often ignored.
Approach: They propose a noise-robust multi-modal interactive fusion approach with cross-modal relation-aware mask mechanism for MNMT.
Outcome: The proposed model achieves state-of-the-art scores in all En-De, En-Fr and En-Cs translation tasks.

Similar Papers

Multimodal Robustness for Neural Machine Translation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to deal with noisy multimodal inputs are not robust enough to deal effectively with noisy data.
Approach: They propose a method that composes domain adapters to deal with noisy inputs . they combine these adapters at runtime via dynamic routing or when source of noise is unknown .
Outcome: The proposed model is flexible and state-of-the-art to deal with noisy multimodal inputs.
Supervised Visual Attention for Multimodal Neural Machine Translation (2020.coling-main)

Copied to clipboard

Challenge: Existing studies show that a conventional visual attention mechanism trained in an unsupervised manner is not effective for multimodal neural machine translation.
Approach: They propose a supervised visual attention mechanism for multimodal neural machine translation that captures the relationship between a word and an image region more precisely than a conventional visual attention system.
Outcome: The proposed model improves on English-German and German-English translation tasks and English-Japanese and Japanese-English tasks using the Flickr30k Entities JP dataset.
Multimodal Neural Machine Translation: A Survey of the State of the Art (2025.emnlp-main)

Copied to clipboard

Challenge: Multimodal neural machine translation (MNMT) is a task that aims to translate text into the target language using neural networks.
Approach: They propose to integrate other modalities with textual data to enhance translation performance.
Outcome: The proposed task aims to integrate visual modality with textual data to improve translation quality.
Entity-level Cross-modal Learning Improves Multi-modal Machine Translation (2021.findings-emnlp)

Copied to clipboard

Challenge: Multi-modal machine translation aims at improving translation performance by incorporating visual information.
Approach: They propose an explicit entity-level cross-modal learning approach that aims to augment the entity representation by combining a translation task and a reconstruction task.
Outcome: The proposed approach achieves comparable or even better performance than state-of-the-art models.
CCIM: Cross-modal Cross-lingual Interactive Image Translation (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing research on text image machine translation (TIMT) lacks recognized source language information resulting in a decrease in translation performance.
Approach: They propose a cross-modal cross-lingual interactive model which incorporates source language information by synchronizing source and target language results.
Outcome: The proposed model outperforms end-to-end models and has faster decoding speed with smaller model size than cascade models.
Learn and Consolidate: Continual Adaptation for Zero-Shot and Multilingual Neural Machine Translation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing multilingual neural machine translation models perform poorly on language pairs with no parallel corpus.
Approach: They propose a two-stage approach that encourages original models to acquire language-agnostic multilingual representations from new data and preserves the model architecture without introducing parameters.
Outcome: The proposed approach improves performance in translation directions where existing models are weak and mitigates degeneration in the well-performing translation directions, offering flexibility in the real-world scenario.
Probing Multi-modal Machine Translation with Pre-trained Language Model (2021.findings-acl)

Copied to clipboard

Challenge: Multi-modal machine translation (MMT) aimed at using images to help disambiguate the target during translation but recent studies showed that visual features are either negligible or incremental.
Approach: They propose to incorporate a visual language model on the source side to improve multi-modal translation quality significantly.
Outcome: The proposed model improves the translation quality significantly on the multi-modal dataset.
ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition (2022.naacl-main)

Copied to clipboard

Challenge: Recent work on Multi-modal Named Entity Recognition (MNER) relies on image information to model interactions between image and text representations.
Approach: They propose to align image features into the textual space to better utilize attention mechanisms . they use regional object tags, captions and optical characters as visual contexts .
Outcome: The proposed model can achieve state-of-the-art accuracy on multi-modal Named Entity Recognition datasets even without image information.
Low-resource Neural Machine Translation with Cross-modal Alignment (2022.emnlp-main)

Copied to clipboard

Challenge: Existing neural machine translation techniques rely on large monolingual corpus, which is costly for some low-resource languages.
Approach: They propose a cross-modal contrastive learning method to learn a shared space for all languages by additional visual modality.
Outcome: The proposed method can learn cross-modal and cross-lingual alignment with small amount of image-text pairs and achieves significant improvements over the text-only baseline.
Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis (2023.emnlp-main)

Copied to clipboard

Challenge: Multimodal Sentiment Analysis (MSA) is effective when using rich information from multiple sources, but the potential sentiment-irrelevant information across modalities may hinder the performance from being further improved.
Approach: They propose an Adaptive Language-guided Multimodal Transformer (ALMT) that learns an irrelevance/conflict-suppressing representation from visual and audio features under guidance of language features at different scales.
Outcome: The proposed model achieves state-of-the-art on several popular datasets and an abundance of ablation shows the effectiveness of the proposed model.

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