Transfer learning, particularly approaches that combine multi-task learning with pre-trained contextualized embeddings and fine-tuning, have advanced the field of Natural Language Processing tremendously in recent years. In this paper we present MaChAmp, a toolkit for easy fine-tuning of contextualized embeddings in multi-task settings. The benefits of MaChAmp are its flexible configuration options, and the support of a variety of natural language processing tasks in a uniform toolkit, from text classification and sequence labeling to dependency parsing, masked language modeling, and text generation.
@article{arxiv.2005.14672,
title = {Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP},
author = {Rob van der Goot and Ahmet Üstün and Alan Ramponi and Ibrahim Sharaf and Barbara Plank},
journal= {arXiv preprint arXiv:2005.14672},
year = {2021}
}
Comments
EACL demo version (MaChAmp 0.2) https://machamp-nlp.github.io/