Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering

Anonymous

TL;DR: We analyze translation artifacts in cross-lingual VQA.

Abstract: Building a reliable visual question answering (VQA) system across different languages is a challenging problem, primarily due to the lack of abundant samples for training. To address this challenge, recent studies have employed machine translation systems for the cross-lingual VQA task. This involves translating the evaluation samples into a source language (usually English) and using monolingual models (i.e., translate-test). However, our analysis reveals that translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. We find that these artifacts can significantly affect the models, confirmed with extensive experiments across diverse models, languages, and translation processes. In light of this, we present straightforward data augmentation strategies that can alleviate the adverse impacts of translation artifacts.

Paper Type: long

Research Area: Multilinguality and Language Diversity

Contribution Types: Model analysis & interpretability, Approaches to low-resource settings

Languages Studied: Bengali, Chinese, English, French, German, Hebrew, Hindi, Indonesian, Korean, Portuguese, Romanian, Russian, Thai