@inproceedings{nguyen-etal-2021-trankit,
title = "Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing",
author = "Nguyen, Minh Van and
Lai, Viet Dac and
Pouran Ben Veyseh, Amir and
Nguyen, Thien Huu",
editor = "Gkatzia, Dimitra and
Seddah, Djam{\'e}",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-demos.10",
doi = "10.18653/v1/2021.eacl-demos.10",
pages = "80--90",
abstract = "We introduce Trankit, a light-weight Transformer-based Toolkit for multilingual Natural Language Processing (NLP). It provides a trainable pipeline for fundamental NLP tasks over 100 languages, and 90 pretrained pipelines for 56 languages. Built on a state-of-the-art pretrained language model, Trankit significantly outperforms prior multilingual NLP pipelines over sentence segmentation, part-of-speech tagging, morphological feature tagging, and dependency parsing while maintaining competitive performance for tokenization, multi-word token expansion, and lemmatization over 90 Universal Dependencies treebanks. Despite the use of a large pretrained transformer, our toolkit is still efficient in memory usage and speed. This is achieved by our novel plug-and-play mechanism with Adapters where a multilingual pretrained transformer is shared across pipelines for different languages. Our toolkit along with pretrained models and code are publicly available at: \url{https://github.com/nlp-uoregon/trankit}. A demo website for our toolkit is also available at: \url{http://nlp.uoregon.edu/trankit}. Finally, we create a demo video for Trankit at: \url{https://youtu.be/q0KGP3zGjGc}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2021-trankit">
<titleInfo>
<title>Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="given">Van</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viet</namePart>
<namePart type="given">Dac</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Pouran Ben Veyseh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="given">Huu</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitra</namePart>
<namePart type="family">Gkatzia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djamé</namePart>
<namePart type="family">Seddah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce Trankit, a light-weight Transformer-based Toolkit for multilingual Natural Language Processing (NLP). It provides a trainable pipeline for fundamental NLP tasks over 100 languages, and 90 pretrained pipelines for 56 languages. Built on a state-of-the-art pretrained language model, Trankit significantly outperforms prior multilingual NLP pipelines over sentence segmentation, part-of-speech tagging, morphological feature tagging, and dependency parsing while maintaining competitive performance for tokenization, multi-word token expansion, and lemmatization over 90 Universal Dependencies treebanks. Despite the use of a large pretrained transformer, our toolkit is still efficient in memory usage and speed. This is achieved by our novel plug-and-play mechanism with Adapters where a multilingual pretrained transformer is shared across pipelines for different languages. Our toolkit along with pretrained models and code are publicly available at: https://github.com/nlp-uoregon/trankit. A demo website for our toolkit is also available at: http://nlp.uoregon.edu/trankit. Finally, we create a demo video for Trankit at: https://youtu.be/q0KGP3zGjGc.</abstract>
<identifier type="citekey">nguyen-etal-2021-trankit</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-demos.10</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-demos.10</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>80</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing
%A Nguyen, Minh Van
%A Lai, Viet Dac
%A Pouran Ben Veyseh, Amir
%A Nguyen, Thien Huu
%Y Gkatzia, Dimitra
%Y Seddah, Djamé
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F nguyen-etal-2021-trankit
%X We introduce Trankit, a light-weight Transformer-based Toolkit for multilingual Natural Language Processing (NLP). It provides a trainable pipeline for fundamental NLP tasks over 100 languages, and 90 pretrained pipelines for 56 languages. Built on a state-of-the-art pretrained language model, Trankit significantly outperforms prior multilingual NLP pipelines over sentence segmentation, part-of-speech tagging, morphological feature tagging, and dependency parsing while maintaining competitive performance for tokenization, multi-word token expansion, and lemmatization over 90 Universal Dependencies treebanks. Despite the use of a large pretrained transformer, our toolkit is still efficient in memory usage and speed. This is achieved by our novel plug-and-play mechanism with Adapters where a multilingual pretrained transformer is shared across pipelines for different languages. Our toolkit along with pretrained models and code are publicly available at: https://github.com/nlp-uoregon/trankit. A demo website for our toolkit is also available at: http://nlp.uoregon.edu/trankit. Finally, we create a demo video for Trankit at: https://youtu.be/q0KGP3zGjGc.
%R 10.18653/v1/2021.eacl-demos.10
%U https://aclanthology.org/2021.eacl-demos.10
%U https://doi.org/10.18653/v1/2021.eacl-demos.10
%P 80-90
Markdown (Informal)
[Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing](https://aclanthology.org/2021.eacl-demos.10) (Nguyen et al., EACL 2021)
ACL