Authors:
Haukur Páll Jónsson
1
and
Hrafn Loftsson
2
Affiliations:
1
Miðeind ehf., Reykjavík, Iceland
;
2
Department of Computer Science, Reykjavik University, Iceland
Keyword(s):
NLP, Multitask, Icelandic, PoS, Lemmatization.
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.