The Social and the Neural Network: How to Make Natural Language Processing about People again

Dirk Hovy


Abstract
Over the years, natural language processing has increasingly focused on tasks that can be solved by statistical models, but ignored the social aspects of language. These limitations are in large part due to historically available data and the limitations of the models, but have narrowed our focus and biased the tools demographically. However, with the increased availability of data sets including socio-demographic information and more expressive (neural) models, we have the opportunity to address both issues. I argue that this combination can broaden the focus of NLP to solve a whole new range of tasks, enable us to generate novel linguistic insights, and provide fairer tools for everyone.
Anthology ID:
W18-1106
Volume:
Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media
Month:
June
Year:
2018
Address:
New Orleans, Louisiana, USA
Venues:
NAACL | PEOPLES | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
42–49
Language:
URL:
https://www.aclweb.org/anthology/W18-1106
DOI:
10.18653/v1/W18-1106
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W18-1106.pdf