TY - JOUR

T1 - Multitask and Multilingual Modelling for Lexical Analysis

AU - Bjerva, Johannes

PY - 2018

Y1 - 2018

N2 - 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.

AB - 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.

KW - Natural language processing

KW - Deep learning

KW - Multitask learning

KW - Multilingual learning

U2 - 10.1007/s13218-018-0557-5

DO - 10.1007/s13218-018-0557-5

M3 - Journal article

VL - 32

SP - 287

EP - 290

JO - KI - Künstliche Intelligenz

JF - KI - Künstliche Intelligenz

SN - 0933-1875

IS - 4

ER -