Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben
Neural Computing and Applications
Erschienen in: Neural Computing and Applications 8/2021

24.07.2020 | Original Article

Extensive study on the underlying gender bias in contextualized word embeddings

verfasst von: Christine Basta, Marta R. Costa-jussà, Noe Casas

Erschienen in: Neural Computing and Applications | Ausgabe 8/2021

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Gender bias is affecting many natural language processing applications. While we are still far from proposing debiasing methods that will solve the problem, we are making progress analyzing the impact of this bias in current algorithms. This paper provides an extensive study of the underlying gender bias in popular contextualized word embeddings. Our study provides an insightful analysis of evaluation measures applied to several English data domains and the layers of the contextualized word embeddings. It is also adapted and extended to the Spanish language. Our study points out the advantages and limitations of the various evaluation measures that we are using and aims to standardize the evaluation of gender bias in contextualized word embeddings.
Vorheriger Artikel Parameterized neural network training for the solution of a class of stiff initial value systems
Nächster Artikel “SPOCU”: scaled polynomial constant unit activation function

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren
Fußnoten
9
Both the ‘biased list’ and ‘extended biased list’ were kindly provided by Hila Gonen to reproduce experiments from her study Gonen and Goldberg [9].
 
Literatur
1.
Basta C, Costa-jussà MR, Casas N (2019) Evaluating the underlying gender bias in contextualized word embeddings. arXiv:​190408783
2.
Blodgett SL, Barocas S, Daumé III H, Wallach H (2020) Language (technology) is power: a critical survey of “bias” in NLP. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 5454–5476
3.
Bolukbasi T, Chang KW, Zou JY, Saligrama V, Kalai AT (2016) Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In: Lee DD, Sugiyama M, Luxburg UV, Guyon I, Garnett R (eds) Advances in Neural Information Processing Systems 29, Curran Associates, Inc., pp 4349–4357
4.
Costa-jussà MR (2019) An analysis of gender bias studies in natural language processing. Nature Machine Intelligence 1
5.
6.
Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:​181004805
7.
Ethayarajh K, Duvenaud D, Hirst G (2019) Understanding undesirable word embedding associations. In: Proc. of the ACL
8.
Font JE, Costa-jussà MR (2019) Equalizing gender biases in neural machine translation with word embeddings techniques. arXiv:​1901.​03116
9.
Gonen H, Goldberg Y (2019) Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them. arXiv:​1903.​03862
10.
11.
Guo W, Caliskan A (2020) Detecting emergent intersectional biases: contextualized word embeddings contain a distribution of human-like biases. arXiv:​200603955
12.
13.
Howard J, Ruder S (2018) Universal language model fine-tuning for text classification. In: Proc. of the ACL (Volume 1: Long Papers), Melbourne, Australia, pp 328–339
14.
Huang L, Sun C, Qiu X, Huang X (2019) GlossBERT: BERT for word sense disambiguation with gloss knowledge. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), Hong Kong, China, pp 3509–3514
15.
16.
Khattak FK, Jeblee S, Pou-Prom C, Abdalla M, Meaney C, Rudzicz F (2019) A survey of word embeddings for clinical text. J Biomed Inf X 4:100057
17.
Kurita K, Vyas N, Pareek A, Black AW, Tsvetkov Y (2019) Measuring bias in contextualized word representations. In: Proceedings of the first workshop on gender bias in natural language processing, pp 166–172
18.
Liu NF, Gardner M, Belinkov Y, Peters ME, Smith NA (2019) Linguistic knowledge and transferability of contextual representations. In: Proceedings of the conference of the north american chapter of the association for computational linguistics: human language technologies
19.
20.
May C, Wang A, Bordia S, Bowman SR, Rudinger R (2019) On measuring social biases in sentence encoders. arXiv:​190310561
21.
McGuire L, Mulvey KL, Goff E, Irvin MJ, Winterbottom M, Fields GE, Hartstone-Rose A, Rutland A (2020) Stem gender stereotypes from early childhood through adolescence at informal science centers. J Appl Develop Psychol 67:101109CrossRef
22.
Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Burges CJC, Bottou L, Welling M, Ghahramani Z, Weinberger KQ (eds) Advances in Neural Information Processing Systems 26, pp 3111–3119
23.
Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP), pp 1532–1543
24.
25.
Peters M, Ruder S, Smith NA (2019) To tune or not to tune? adapting pretrained representations to diverse tasks. arXiv:​190305987
26.
27.
Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I (2019) Language models are unsupervised multitask learners
28.
Smith NA (2020) Contextual word representations: putting words into computers. Commun ACM 63(6):66–74CrossRef
29.
Stanovsky G, Smith NA, Zettlemoyer L (2019) Evaluating gender bias in machine translation. In: Proc. of the ACL, Florence, Italy, pp 1679–1684
30.
Tan YC, Celis LE (2019) Assessing social and intersectional biases in contextualized word representations. In: Advances in Neural Information Processing Systems, pp 13209–13220
31.
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998–6008
32.
Zhang BH, Lemoine B, Mitchell M (2018) Mitigating unwanted biases with adversarial learning. In: Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, ACM, pp 335–340
33.
Zhao J, Wang T, Yatskar M, Ordonez V, Chang KW (2018a) Gender bias in coreference resolution: evaluation and debiasing methods. arXiv:​180406876
34.
35.
Zhao J, Wang T, Yatskar M, Cotterell R, Ordonez V, Chang KW (2019) Gender bias in contextualized word embeddings. In: Proc. of the Conference of the NAACL
36.
Zhou P, Shi W, Zhao J, Huang KH, Chen M, Cotterell R, Chang KW (2019) Examining gender bias in languages with grammatical gender. arXiv:​190902224
Metadaten
Titel
Extensive study on the underlying gender bias in contextualized word embeddings
verfasst von
Christine Basta
Marta R. Costa-jussà
Noe Casas
Publikationsdatum
24.07.2020
Verlag
Springer London
Erschienen in
Neural Computing and Applications / Ausgabe 8/2021
Print ISSN: 0941-0643
Elektronische ISSN: 1433-3058
DOI
https://doi.org/10.1007/s00521-020-05211-z

Weitere Artikel der Ausgabe 8/2021

Neural Computing and Applications 8/2021 Zur Ausgabe

Original Article

SHEG: summarization and headline generation of news articles using deep learning

Original Article

A neural integrator model for planning and value-based decision making of a robotics assistant

Original Article

Time-aware user profiling from personal service ecosystem

Original Article

Convergence analysis on time scales for HOBAM neural networks in the Stepanov-like weighted pseudo almost automorphic space

Original Article

Evaluation of computationally intelligent techniques for breast cancer diagnosis

Original Article

How frontal is a face? Quantitative estimation of face pose based on CNN and geometric projection