Multitask and Multilingual Modelling for Lexical Analysis
This work addresses data scarcity in NLP for multiple languages and tasks, but it appears incremental as it builds on existing concepts of relatedness.
The paper tackled the problem of building NLP models that require less manually annotated data by exploring joint multitask and multilingual modeling across 60 languages, showing potential for improved efficiency and linguistic insights.
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.