Evjvqa Challenge: Multilingual Visual Question Answering

Abstract

Visual Question Answering (VQA) is a challenging task of natural language processing (NLP) and computer vision (CV), attracting significant attention from researchers. English is a resource-rich language that has witnessed various developments in datasets and models for visual question answering. Visual question answering in other languages also would be developed for resources and models. In addition, there is no multilingual dataset targeting the visual content of a particular country with its own objects and cultural characteristics. To address the weakness, we provide the research community with a benchmark dataset named EVJVQA, including 33,000+ pairs of question-answer over three languages: Vietnamese, English, and Japanese, on approximately 5,000 images taken from Vietnam for evaluating multilingual VQA systems or models. EVJVQA is used as a benchmark dataset for the challenge of multilingual visual question answering at the 9th Workshop on Vietnamese Language and Speech Processing (VLSP 2022). This task attracted 62 participant teams from various universities and organizations. In this article, we present details of the organization of the challenge, an overview of the methods employed by shared-task participants, and the results. The highest performances are 0.4392 in F1-score and 0.4009 in BLUE on the private test set. The multilingual QA systems proposed by the top 2 teams use ViT for the pre-trained vision model and mT5 for the pre-trained language model, a powerful pre-trained language model based on the transformer architecture. EVJVQA is a challenging dataset that motivates NLP and CV researchers to further explore the multilingual models or systems for visual question answering systems.

ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese

“…Consistent with the preceding research conducted by [7,19,22,34], elucidating the evaluation metrics utilized for gauging the model's efficacy is crucial before delving into the analysis of the experimental outcomes. The appraisal in this research encompasses four pivotal performance metrics: F1 score, Precision, Recall, and Accuracy.…”

“…Building on these foundational steps, Nguyen et al in 2022 [34] broke new ground by unveiling a multilingual dataset through a shared task. Notably, this dataset incorporates the Vietnamese language, broadening the scope of VQA research to delve into the Vietnamese linguistic setting.…”

Ohyeah at Vlsp2022-Evjvqa Challenge: a Jointly Language-Image Model for Multilingual Visual Question Answering

“…In our experiment, we used UIT-EVJVQA [26], the first mVQA dataset with three languages, including English and Vietnamese released by VLSP-2022 Organizers for EVJVQA challenge (https://vlsp.org.vn/vlsp2022/eval/evjvqa). This dataset includes question-answer pairs created by humans on a set of images taken in Vietnam, with the answer created from the input question and the corresponding image.…”