Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing
CrossMind.ai logo

Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing

Jan 14, 2021
|
29 views
|
Details
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. Authors: Minh Van Nguyen, Viet Lai, Amir Pouran Ben Veyseh, Thien Huu Nguyen (University of Oregon)

Comments
loading...