Classist Tools: Social Class Correlates with Performance in NLP

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Curry, Amanda Cercas, Attanasio, Giuseppe, Talat, Zeerak, Hovy, Dirk
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910357229928448
author Curry, Amanda Cercas
Attanasio, Giuseppe
Talat, Zeerak
Hovy, Dirk
author_facet Curry, Amanda Cercas
Attanasio, Giuseppe
Talat, Zeerak
Hovy, Dirk
contents Since the foundational work of William Labov on the social stratification of language (Labov, 1964), linguistics has made concentrated efforts to explore the links between sociodemographic characteristics and language production and perception. But while there is strong evidence for socio-demographic characteristics in language, they are infrequently used in Natural Language Processing (NLP). Age and gender are somewhat well represented, but Labov's original target, socioeconomic status, is noticeably absent. And yet it matters. We show empirically that NLP disadvantages less-privileged socioeconomic groups. We annotate a corpus of 95K utterances from movies with social class, ethnicity and geographical language variety and measure the performance of NLP systems on three tasks: language modelling, automatic speech recognition, and grammar error correction. We find significant performance disparities that can be attributed to socioeconomic status as well as ethnicity and geographical differences. With NLP technologies becoming ever more ubiquitous and quotidian, they must accommodate all language varieties to avoid disadvantaging already marginalised groups. We argue for the inclusion of socioeconomic class in future language technologies.
format Preprint
id arxiv_https___arxiv_org_abs_2403_04445
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Classist Tools: Social Class Correlates with Performance in NLP
Curry, Amanda Cercas
Attanasio, Giuseppe
Talat, Zeerak
Hovy, Dirk
Computation and Language
Since the foundational work of William Labov on the social stratification of language (Labov, 1964), linguistics has made concentrated efforts to explore the links between sociodemographic characteristics and language production and perception. But while there is strong evidence for socio-demographic characteristics in language, they are infrequently used in Natural Language Processing (NLP). Age and gender are somewhat well represented, but Labov's original target, socioeconomic status, is noticeably absent. And yet it matters. We show empirically that NLP disadvantages less-privileged socioeconomic groups. We annotate a corpus of 95K utterances from movies with social class, ethnicity and geographical language variety and measure the performance of NLP systems on three tasks: language modelling, automatic speech recognition, and grammar error correction. We find significant performance disparities that can be attributed to socioeconomic status as well as ethnicity and geographical differences. With NLP technologies becoming ever more ubiquitous and quotidian, they must accommodate all language varieties to avoid disadvantaging already marginalised groups. We argue for the inclusion of socioeconomic class in future language technologies.
title Classist Tools: Social Class Correlates with Performance in NLP
topic Computation and Language
url https://arxiv.org/abs/2403.04445