Tóm tắt:

In this paper, we propose applying a jointly developed model to the task of multilingual visual question answering. Specifically, we conduct experiments on a multimodal sequence-to-sequence transformer model derived from the T5 encoder-decoder architecture. Text tokens and Vision Transformer (ViT) dense image embeddings are inputs to an encoder then we used a decoder to automatically anticipate discrete text tokens. We achieved the F1-score of 0.4349 on the private test set and ranked 2nd in the EVJVQA task at the VLSP shared task 2022. For reproducing the result, the code can be found at https://github.com/DinhLuan14/VLSP2022-VQA-OhYeah.