https://github.com/pegasus-lynx/mwe-bpe

BPE beyond Word Boundary: How NOT to use Multi‑Word Expressions in NMT
https://github.com/pegasus-lynx/mwe-bpe

natural-language-processing neural-machine-translation tokenization transformers

Last synced: 2 months ago
JSON representation

BPE beyond Word Boundary: How NOT to use Multi‑Word Expressions in NMT

• Host: GitHub
• URL: https://github.com/pegasus-lynx/mwe-bpe
• Owner: pegasus-lynx
• Created: 2020-12-22T14:01:35.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2022-03-27T21:53:05.000Z (almost 3 years ago)
• Last Synced: 2024-10-21T05:23:52.631Z (3 months ago)
• Topics: natural-language-processing, neural-machine-translation, tokenization, transformers
• Language: Python
• Homepage: https://aclanthology.org/2022.insights-1.24/
• Size: 1.5 MB
• Stars: 4
• Watchers: 2
• Forks: 0
• Open Issues: 0

Awesome Lists containing this project