publications

2022

  1. AIES
    American==White in Multimodal Language-and-Image AI
    Wolfe, Robert, and Caliskan, Aylin
    Artificial Intelligence, Ethics, and Society 2022
    PDF
  2. AIES
    Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics
    Caliskan, Aylin, Ajay, Pimparkar Parth, Charlesworth, Tessa, Wolfe, Robert, and Banaji, Mahzarin R.
    Artificial Intelligence, Ethics, and Society 2022
    PDF
  3. ACM FAccT
    Markedness in Visual Semantic AI
    Wolfe, Robert, and Caliskan, Aylin
    ACM Conference on Fairness, Accountability, and Transparency 2022
    HTML PDF
  4. ACM FAccT
    Evidence for Hypodescent in Visual Semantic AI
    Wolfe, Robert, Banaji, Mahzarin R., and Caliskan, Aylin
    ACM Conference on Fairness, Accountability, and Transparency 2022
    HTML PDF
  5. ACL
    Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations
    Wolfe, Robert, and Caliskan, Aylin
    Association for Computational Linguistics (ACL) 2022
    HTML PDF
  6. AAAI
    VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models
    Wolfe, Robert, and Caliskan, Aylin
    Association for the Advancement of Artificial Intelligence (AAAI) 2022
    HTML PDF
  7. ICSC
    Detecting Emerging Associations and Behaviors in Regional and Diachronic Word Embeddings
    Wolfe, Robert, and Caliskan, Aylin
    IEEE International Conference on Semantic Computing (ICSC) 2022
    HTML

2021

  1. EMNLP
    Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models
    Wolfe, Robert, and Caliskan, Aylin
    Empirical Methods in Natural Language Processing (EMNLP) 2021
    HTML PDF