A PyTorch implementation based on Fairseq and Efficient Wait-k.
Code is in examples/word_waitk.
@inproceedings{kim-cho-2023-enhanced,
title = "Enhanced Simultaneous Machine Translation with Word-level Policies",
author = "Kim, Kang and
Cho, Hankyu",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.1045",
pages = "15616--15634",
}