# Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task

Source: [Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task](<https://www.sota2.com/research/paper/68fa689f1e209131cea1d2dd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:41:59.280Z

Authors: Alireza Mohammadshahi, Remi Lebret, Karl Aberer

Published: 2019-10-08T09:13:39.000Z

## Abstract

In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint embedding space while adapting the alignment of word embeddings between existing languages in our model. We show that our approach enables better generalization, achieving state-of-the-art performance in text-to-image and image-to-text retrieval task, and caption-caption similarity task. Two multimodal multilingual datasets are used for evaluation: Multi30k with German and English captions and Microsoft-COCO with English and Japanese captions.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1910.03291>)

[PDF](<https://arxiv.org/pdf/1910.03291.pdf>)