DMS: A System for Delivering Dynamic Multitask NLP Tools

Haukur Jónsson, Hrafn Loftsson

2022

Abstract

Most NLP frameworks focus on state-of-the-art models which solve a single task. As an alternative to these frameworks, we present the Dynamic Multitask System (DMS), based on native PyTorch. The DMS has a simple interface, can be combined with other frameworks, is easily extendable, and bundles model downloading with an API and a terminal client for end-users. The DMS is flexible towards different tasks and enables quick experimentation with different architectures and hyperparameters. Components of the system are split into two categories with their respective interfaces: encoders and decoders. The DMS targets researchers and practitioners who want to develop state-of-the-art multitask NLP tools and easily supply them to end-users. In this paper, we, first, describe the core components of the DMS and how it can be used to deliver a trained system. Second, we demonstrate how we used the DMS for developing a state-of-the-art PoS tagger and a lemmatizer for Icelandic.

Paper Citation

in Harvard Style

Jónsson H. and Loftsson H. (2022). DMS: A System for Delivering Dynamic Multitask NLP Tools. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI, ISBN 978-989-758-547-0, pages 504-510. DOI: 10.5220/0011005000003116

in Bibtex Style

@conference{nlpinai22,
author={Haukur Jónsson and Hrafn Loftsson},
title={DMS: A System for Delivering Dynamic Multitask NLP Tools},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,},
year={2022},
pages={504-510},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011005000003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,
TI - DMS: A System for Delivering Dynamic Multitask NLP Tools
SN - 978-989-758-547-0
AU - Jónsson H.
AU - Loftsson H.
PY - 2022
SP - 504
EP - 510
DO - 10.5220/0011005000003116