Challenge: Existing multimodal corpora lack the ability to be used in multilingual or non-English scenarios.
Approach: They extend a Flickr30k Entities image-caption dataset with Japanese translations to provide a multilingual corpus.
Outcome: The proposed dataset is the first multilingual image-caption dataset with Japanese translations.

Similar Papers

Adding Syntactic Annotations to Flickr30k Entities Corpus for Multimodal Ambiguous Prepositional-Phrase Attachment Resolution (L18-1)

Copied to clipboard

Challenge: Using visual features extracted from an image, we propose to study the joint processing of image and language features for the Preposition-Phrase attachment disambiguation task.
Approach: They propose to add syntactic annotations to the captions of the Flickr30k Entities corpus to study the joint processing of image and language features for the Preposition-Phrase attachment disambiguation task.
Outcome: The proposed framework is based on the captions of the Flickr30k Entities corpus and is automatically projected on their French and German translations.
Cross-lingual Cross-modal Pretraining for Multimodal Retrieval (2021.naacl-main)

Copied to clipboard

Challenge: Recent pretrained vision-language models have achieved impressive performance on cross-modal retrieval tasks in English.
Approach: They propose a new approach to learn cross-lingual cross-modal representations for matching images and captions in multiple languages using an annotated corpus.
Outcome: The proposed model achieves impressive performance on two multimodal multilingual image caption benchmarks: Multi30k with German captions and MSCOCO with Japanese captions.
Framed Multi30K: A Frame-Based Multimodal-Multilingual Dataset (2024.lrec-main)

Copied to clipboard

Challenge: Recent advances in image-captioning datasets combine image and language to solve a diverse range of tasks.
Approach: They propose a Brazilian Portuguese multimodal-multilingual dataset that extends the Multi30K dataset with 158,915 original Brazilian Portuguese descriptions and 30,104 Brazilian Portuguese translations.
Outcome: The proposed dataset adds 2,677,613 frame evocation labels to the 158,915 English descriptions and to the ones created for Brazilian Portuguese.
Multilingual Image Corpus – Towards a Multimodal and Multilingual Dataset (2022.lrec-1)

Copied to clipboard

Challenge: The goal of the project Multilingual Image Corpus is to provide a large image dataset with annotated objects and object descriptions in 24 languages.
Approach: They propose to provide a large image dataset with annotated objects and object descriptions in 24 languages.
Outcome: The project provides a large image dataset with annotated objects and object descriptions in 24 languages.
Learning Translations via Images with a Massively Multilingual Image Dataset (P18-1)

Copied to clipboard

Challenge: Existing datasets for learning translations of words are limited to a few high-resource languages and unrealistically easy settings.
Approach: They propose a large-scale multilingual corpus of images labeled with the word they represent to facilitate translation research.
Outcome: The proposed method improves on an unsupervised technique that has been limited to a few languages and unrealistic settings.
Entity Linking in 100 Languages (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to multilingual entity linking are cross-lingual, with a focus on zero-shot evaluation.
Approach: They propose a new formulation for multilingual entity linking where language-specific mentions resolve to a language-agnostic Knowledge Base.
Outcome: The proposed model outperforms state-of-the-art models on a large multilingual dataset and shows that frequency-based analysis provided key insights for the model and training enhancements.
Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset (2022.emnlp-main)

Copied to clipboard

Challenge: Existing studies on multilingual image captioning have been hampered by a lack of high-quality evaluation datasets.
Approach: They present a dataset of 3600 images annotated with human-generated captions in 36 languages.
Outcome: The proposed dataset shows that it is feasible to build multilingual image captioning models trained on machine-translated data.
Developing Japanese CLIP Models Leveraging an Open-weight LLM for Large-scale Dataset Translation (2025.naacl-srw)

Copied to clipboard

Challenge: lack of large-scale open Japanese image-text pairs poses a significant barrier to the development of vision-language models.
Approach: They construct large-scale Japanese image-text pairs using machine translation and pre-trained CLIP models on a Japanese dataset.
Outcome: The results show that pre-trained models achieve competitive average scores on Japanese culture tasks compared to models of similar size.
Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task (D19-66)

Copied to clipboard

Challenge: Existing methods to learn multimodal multilingual embeddings for text and image retrieval tasks are limited to English.
Approach: They propose a new approach to learn multimodal multilingual embeddings for matching images and captions in two languages by combing two existing objective functions and adapting alignment between existing languages.
Outcome: The proposed model achieves state-of-the-art in retrieval and caption-caption tasks while adapting existing language alignments.
Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task (D19-64)

Copied to clipboard

Challenge: Existing methods to learn multimodal multilingual embeddings for text and image retrieval tasks are limited to English.
Approach: They propose a new approach to learn multimodal multilingual embeddings for matching images and captions in two languages by combing two existing objective functions and adapting alignment between existing languages.
Outcome: The proposed model achieves state-of-the-art in retrieval and caption-caption tasks while adapting existing language alignments.

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