Skip to content

Add Miyazaki et al. 2024 (Gloss Pair Encoding) to Text-to-Gloss #147

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
AmitMY merged 2 commits into from
Apr 28, 2026
Merged

Add Miyazaki et al. 2024 (Gloss Pair Encoding) to Text-to-Gloss #147

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ffab339
Add Miyazaki et al. 2024 (Gloss Pair Encoding) to Text-to-Gloss
AmitMY Apr 28, 2026
f5b7ef9
Simplify miyazaki-etal one-liner (review pattern: concise)
AmitMY Apr 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions src/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -725,6 +725,8 @@ complexity of the model.
Testing their model on the RWTH-PHOENIX-Weather-2014T [@cihan2018neural],
they demonstrated that injecting this additional information results in better translation quality.

@miyazaki-etal-2024-sign propose Gloss Pair Encoding (GPE), a BPE-inspired tokenization that merges frequent gloss pairs into single tokens to better match granularity between spoken and signed languages, and show that combining GPE-augmented data with the original training data improves text-to-gloss translation on a Japanese-JSL corpus.

---

#### Video-to-Text
Expand Down
12 changes: 12 additions & 0 deletions src/references.bib
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4554,6 +4554,14 @@ @inproceedings{roh-etal-2024-preprocessing
Hwang, Eui Jun and
Cho, Sukmin and
Park, Jong C.",
}

@inproceedings{miyazaki-etal-2024-sign,
title = "Sign Language Translation with Gloss Pair Encoding",
author = "Miyazaki, Taro and
Tan, Sihan and
Uchida, Tsubasa and
Kaneko, Hiroyuki",
editor = "Efthimiou, Eleni and
Fotinea, Stavroula-Evita and
Hanke, Thomas and
Expand All @@ -4572,3 +4580,7 @@ @inproceedings{roh-etal-2024-preprocessing
url = "https://aclanthology.org/2024.signlang-1.36/",
pages = "323--334"
}

url = "https://aclanthology.org/2024.signlang-1.29/",
pages = "262--268"
}
Loading