Is a Prestigious Job the same as a Prestigious Country? A Case Study on Multilingual Sentence Embeddings and European Countries

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475750" target="_blank" >RIV/00216208:11320/23:10475750 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2023.findings-emnlp.71.pdf" target="_blank" >https://aclanthology.org/2023.findings-emnlp.71.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Is a Prestigious Job the same as a Prestigious Country? A Case Study on Multilingual Sentence Embeddings and European Countries

Original language description

We study how multilingual sentence representations capture European countries and occupations and how this differs across European languages. We prompt the models with templated sentences that we machine-translate into 12 European languages and analyze the most prominent dimensions in the embeddings. Our analysis reveals that the most prominent feature in the embedding is the geopolitical distinction between Eastern and Western Europe and the country&apos;s economic strength in terms of GDP. When prompted specifically for job prestige, the embedding space clearly distinguishes high and low-prestige jobs. The occupational dimension is uncorrelated with the most dominant country dimensions in three out of four studied models. The exception is a small distilled model that exhibits a connection between occupational prestige and country of origin, which is a potential source of nationality-based discrimination. Our findings are consistent across languages.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Findings of the Association for Computational Linguistics: EMNLP 2023

ISBN

978-1-955917-71-1

ISSN

—

e-ISSN

—

Number of pages

11

Pages from-to

1000-1010

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg, PA, USA

Event location

Singapore, Singapore

Event date

Dec 6, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—