CSDL Bài trích Báo - Tạp chí

Trở về

A study of data augmentation and accuracy improvement in machine translation for Vietnamese sign language

Tác giả: Thi Bich Diep Nguyen, Trung Nghia Phung, Tat Thang Vu
Số trang: P. 143-158
Số phát hành: Tập 39 - Số 2
Kiểu tài liệu: Tạp chí trong nước
Nơi lưu trữ: 03 Quang Trung
Mã phân loại: 005
Ngôn ngữ: English
Từ khóa: Natural language processing, machine translation, Vietnamese sign language, data augmentation, data enrichment
Chủ đề: Sign language
Tóm tắt:

In this paper, we experimented with and proposed several methods for building and improving models for the VL to VSL translation task. We presented a data augmentation method to improve the performance of our neural machine translation models. Using an initial dataset of 10k bilingual sentence pairs, we were able to obtain a new dataset of 60k sentence pairs with a perplexity score no more than 1.5 times that of the original dataset.

Tạp chí liên quan