Unsupervised Bilingual Lexicon Induction from Mono-lingual Multimodal Data

TL;DR

This paper introduces a novel unsupervised method for bilingual lexicon induction using multilingual caption models trained on monolingual multimodal data, leveraging both linguistic and localized visual features to improve translation accuracy.

Contribution

It proposes a multi-lingual caption model that jointly learns linguistic and visual features from monolingual multimodal data, enabling unsupervised bilingual lexicon induction without parallel corpora.

Findings

Outperforms previous vision-based methods on multiple language pairs.

Effectively learns translations for less visual-relevant words.

Utilizes both linguistic context and localized visual features for better translation.

Abstract

Bilingual lexicon induction, translating words from the source language to the target language, is a long-standing natural language processing task. Recent endeavors prove that it is promising to employ images as pivot to learn the lexicon induction without reliance on parallel corpora. However, these vision-based approaches simply associate words with entire images, which are constrained to translate concrete words and require object-centered images. We humans can understand words better when they are within a sentence with context. Therefore, in this paper, we propose to utilize images and their associated captions to address the limitations of previous approaches. We propose a multi-lingual caption model trained with different mono-lingual multimodal data to map words in different languages into joint spaces. Two types of word representation are induced from the multi-lingual caption model: linguistic features and localized visual features. The linguistic feature is learned from the sentence contexts with visual semantic constraints, which is beneficial to learn translation for words that are less visual-relevant. The localized visual feature is attended to the region in the image that correlates to the word, so that it alleviates the image restriction for salient visual representation. The two types of features are complementary for word translation. Experimental results on multiple language pairs demonstrate the effectiveness of our proposed method, which substantially outperforms previous vision-based approaches without using any parallel sentences or supervision of seed word pairs.