Massive Choice, Ample Tasks (MaChAmp)
This websites introduces MaChAmp and provides an overview of code and papers that use MaChAmp. We are proud to annouce that MaChAmp has received an EACL 2021 outstanding paper award (demo track)!
Abstract
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.
Contributors
Acknowledgments
This research was supported by an Amazon Research Award, an STSM in the Multi3Generation COST action (CA18231), a visit supported by COSBI, grant 9063-00077B (Danmarks Frie Forskningsfond), and Nvidia corporation for sponsoring Titan GPUs. We thank the NLPL laboratory and the HPC team at ITU for the computational resources used in this work.
Papers that use MaChAmp
v0.1
- Biomedical Event Extraction as Sequence Labeling (EMNLP 2020)
- Character-level Representations Improve DRS-based Semantic Parsing Even in the Age of BERT (EMNLP 2020)
- DaN+: Danish Nested Named Entities and Lexical Normalization (Coling 2020)
v0.2
- Challenges in Annotating and Parsing Spoken, Code-switched, Frisian-Dutch Data (Adapt-NLP 2021)
- Lexical Normalization for Code-switched Data and its Effect on POS-tagging (EACL 2021)
- From Masked-Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding (NAACL 2021)
- De-identification of Privacy-related Entities in Job Postings (NoDaLiDa 2021)
- Cross-Lingual Cross-Domain Nested Named Entity Evaluation on English Web Texts (ACL 2021 Findings)
- Genre as Weak Supervision for Cross-lingual Dependency Parsing (EMNLP 2021)
Citation
@inproceedings{van-der-goot-etal-2021-massive,
title = "Massive Choice, Ample Tasks ({M}a{C}h{A}mp): A Toolkit for Multi-task Learning in {NLP}",
author = {van der Goot, Rob and
{\"U}st{\"u}n, Ahmet and
Ramponi, Alan and
Sharaf, Ibrahim and
Plank, Barbara},
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://www.aclweb.org/anthology/2021.eacl-demos.22",
pages = "176--197",
}