Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations

TL;DR

This paper introduces a novel multi-head attention model with diversity constraints to improve grounded multilingual multimodal representations, enhancing image-text matching and semantic similarity tasks across languages.

Contribution

It proposes a diverse multi-head attention mechanism and a new objective function to better align multilingual textual and visual information.

Findings

Significant performance improvements in German-Image and English-Image matching tasks.

Enhanced semantic textual similarity scores with the proposed model.

Effective learning of fine-grained visual-semantic alignments.

Abstract

With the aim of promoting and understanding the multilingual version of image search, we leverage visual object detection and propose a model with diverse multi-head attention to learn grounded multilingual multimodal representations. Specifically, our model attends to different types of textual semantics in two languages and visual objects for fine-grained alignments between sentences and images. We introduce a new objective function which explicitly encourages attention diversity to learn an improved visual-semantic embedding space. We evaluate our model in the German-Image and English-Image matching tasks on the Multi30K dataset, and in the Semantic Textual Similarity task with the English descriptions of visual content. Results show that our model yields a significant performance gain over other methods in all of the three tasks.