Multitask and Multilingual Modelling for Lexical Analysis

TL;DR

This paper explores how multitask and multilingual modeling can improve NLP tasks across 60 languages, reducing the need for extensive manual annotation and revealing linguistic insights.

Contribution

It demonstrates the potential of joint multitask and multilingual models for NLP, leveraging language relatedness to enhance performance and reduce annotation effort.

Findings

Potential for improved NLP performance across multiple languages

Hints at linguistic insights from multilingual models

Reduced need for manual annotation in NLP tasks

Abstract

In Natural Language Processing (NLP), one traditionally considers a single task (e.g. part-of-speech tagging) for a single language (e.g. English) at a time. However, recent work has shown that it can be beneficial to take advantage of relatedness between tasks, as well as between languages. In this work I examine the concept of relatedness and explore how it can be utilised to build NLP models that require less manually annotated data. A large selection of NLP tasks is investigated for a substantial language sample comprising 60 languages. The results show potential for joint multitask and multilingual modelling, and hints at linguistic insights which can be gained from such models.