Nothing Special   »   [go: up one dir, main page]

YANMTT: Yet Another Neural Machine Translation Toolkit

Raj Dabre, Diptesh Kanojia, Chinmay Sawant, Eiichiro Sumita


Abstract
In this paper, we present our open-source neural machine translation (NMT) toolkit called “Yet Another Neural Machine Translation Toolkit” abbreviated as YANMTT - https://github.com/prajdabre/yanmtt, which is built on top of the HuggingFace Transformers library. YANMTT focuses on transfer learning and enables easy pre-training and fine-tuning of sequence-to-sequence models at scale. It can be used for training parameter-heavy models with minimal parameter sharing and efficient, lightweight models via heavy parameter sharing. Additionally, it supports parameter-efficient fine-tuning (PEFT) through adapters and prompts. Our toolkit also comes with a user interface that can be used to demonstrate these models and visualize various parts of the model. Apart from these core features, our toolkit also provides other advanced functionalities such as but not limited to document/multi-source NMT, simultaneous NMT, mixtures-of-experts, model compression and continual learning.
Anthology ID:
2023.acl-demo.24
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Danushka Bollegala, Ruihong Huang, Alan Ritter
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
257–263
Language:
URL:
https://aclanthology.org/2023.acl-demo.24
DOI:
10.18653/v1/2023.acl-demo.24
Bibkey:
Cite (ACL):
Raj Dabre, Diptesh Kanojia, Chinmay Sawant, and Eiichiro Sumita. 2023. YANMTT: Yet Another Neural Machine Translation Toolkit. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 257–263, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
YANMTT: Yet Another Neural Machine Translation Toolkit (Dabre et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-demo.24.pdf
Video:
 https://aclanthology.org/2023.acl-demo.24.mp4