MétaCan
Menu
Back to cohort

Mitigating Language-Dependent Ethnic Bias in BERT

2021· preprint· en· W3201341200 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueProceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · 2021
Typepreprint
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsKootenay Association for Science & Technology
FundersMinistry of Science and ICT, South KoreaNational Research Foundation of KoreaNational Research Foundation
KeywordsCategorical variableComputer scienceEthnic groupGermanTurkishNatural language processingMetric (unit)Language modelLinguisticsArabicGender biasWord (group theory)Artificial intelligencePsychologyMachine learningSociologySocial psychology

Abstract

fetched live from OpenAlex

BERT and other large-scale language models (LMs) contain gender and racial bias. They also exhibit other dimensions of social bias, most of which have not been studied in depth, and some of which vary depending on the language. In this paper, we study ethnic bias and how it varies across languages by analyzing and mitigating ethnic bias in monolingual BERT for English, German, Spanish, Korean, Turkish, and Chinese. To observe and quantify ethnic bias, we develop a novel metric called Categorical Bias score. Then we propose two methods for mitigation; first using a multilingual model, and second using contextual word alignment of two monolingual models. We compare our proposed methods with monolingual BERT and show that these methods effectively alleviate the ethnic bias. Which of the two methods works better depends on the amount of NLP resources available for that language. We additionally experiment with Arabic and Greek to verify that our proposed methods work for a wider variety of languages.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.005
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Research integrity
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.897
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.005
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.002
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0030.004
Research integrity0.0010.004
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.139
GPT teacher head0.443
Teacher spread0.304 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it