CSDL Bài trích Báo - Tạp chí
Ohyeah at VLSP2022-EVJVQA challenge: a jointly language-image model for multilingual visual question answering
Tác giả: Luan Ngo Dinh, Hieu Le Ngoc, Long Quoc Phan
Số trang:
P. 381-392
Số phát hành:
Tập 39 - Số 4
Kiểu tài liệu:
Tạp chí trong nước
Nơi lưu trữ:
03 Quang Trung
Mã phân loại:
005
Ngôn ngữ:
Tiếng Anh
Từ khóa:
Machine reading comprehension, question answering
Chủ đề:
Computer program language
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.