Towards Zero-shot Cross-lingual Image Retrieval

Abstract

There has been a recent spike in interest in multi-modal Language and Vision problems. On the language side, most of these models primarily focus on English since most multi-modal datasets are monolingual. We try to bridge this gap with a zero-shot approach for learning multi-modal representations using cross-lingual pre-training on the text side. We present a simple yet practical approach for building a cross-lingual image retrieval model which trains on a monolingual training dataset but can be used in a zero-shot cross-lingual fashion during inference. We also introduce a new objective function which tightens the text embedding clusters by pushing dissimilar texts from each other. Finally, we introduce a new 1K multi-lingual MSCOCO2014 caption test dataset (XTD10) in 7 languages that we collected using a crowdsourcing platform. We use this as the test set for evaluating zero-shot model performance across languages. XTD10 dataset is made publicly available here: https://github.com/adobe-research/Cross-lingual-Test-Dataset-XTD10

References in corpus (7)

• Unsupervised Machine Translation Using Monolingual Corpora Only
• AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
• Visual Search at eBay
• Multilingual Universal Sentence Encoder for Semantic Retrieval
• Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce
• Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task
• Multitask Text-to-Visual Embedding with Titles and Clickthrough Data

Cited by in corpus (4)

• Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning
• MURAL: Multimodal, Multitask Retrieval Across Languages
• Translation-Enhanced Multilingual Text-to-Image Generation
• Towards Zero-shot Cross-lingual Image Retrieval and Tagging