@inproceedings{dabre-etal-2023-yanmtt,
title = "{YANMTT}: Yet Another Neural Machine Translation Toolkit",
author = "Dabre, Raj and
Kanojia, Diptesh and
Sawant, Chinmay and
Sumita, Eiichiro",
editor = "Bollegala, Danushka and
Huang, Ruihong and
Ritter, Alan",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-demo.24",
doi = "10.18653/v1/2023.acl-demo.24",
pages = "257--263",
abstract = "In this paper, we present our open-source neural machine translation (NMT) toolkit called {``}Yet Another Neural Machine Translation Toolkit{''} abbreviated as YANMTT - \url{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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dabre-etal-2023-yanmtt">
<titleInfo>
<title>YANMTT: Yet Another Neural Machine Translation Toolkit</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diptesh</namePart>
<namePart type="family">Kanojia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chinmay</namePart>
<namePart type="family">Sawant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danushka</namePart>
<namePart type="family">Bollegala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">dabre-etal-2023-yanmtt</identifier>
<identifier type="doi">10.18653/v1/2023.acl-demo.24</identifier>
<location>
<url>https://aclanthology.org/2023.acl-demo.24</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>257</start>
<end>263</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YANMTT: Yet Another Neural Machine Translation Toolkit
%A Dabre, Raj
%A Kanojia, Diptesh
%A Sawant, Chinmay
%A Sumita, Eiichiro
%Y Bollegala, Danushka
%Y Huang, Ruihong
%Y Ritter, Alan
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F dabre-etal-2023-yanmtt
%X 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.
%R 10.18653/v1/2023.acl-demo.24
%U https://aclanthology.org/2023.acl-demo.24
%U https://doi.org/10.18653/v1/2023.acl-demo.24
%P 257-263
Markdown (Informal)
[YANMTT: Yet Another Neural Machine Translation Toolkit](https://aclanthology.org/2023.acl-demo.24) (Dabre et al., ACL 2023)
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.