Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing
This toolkit provides improved performance for fundamental multilingual NLP tasks for researchers and developers working with diverse languages, offering a competitive advantage over existing solutions.
This paper introduces Trankit, a light-weight Transformer-based toolkit for multilingual NLP, offering a trainable pipeline for over 100 languages and 90 pretrained pipelines for 56 languages. It significantly outperforms prior multilingual NLP pipelines on sentence segmentation, part-of-speech tagging, morphological feature tagging, and dependency parsing across 90 Universal Dependencies treebanks.
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.