Trankit: A light-weight transformer-based toolkit for multilingual natural language processing

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440926" target="_blank" >RIV/00216208:11320/21:10440926 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Trankit: A light-weight transformer-based toolkit for multilingual natural language processing

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the System Demonstrations

ISBN

978-1-954085-05-3

ISSN

—

e-ISSN

—

Number of pages

11

Pages from-to

80-90

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg

Event location

online

Event date

Apr 19, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—