Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models

1 October 2021

Papers citing "Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models"

3 / 3 papers shown

Title
CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters Hicham El Boukkouri Olivier Ferret Thomas Lavergne Hiroshi Noji Pierre Zweigenbaum Junichi Tsujii 52 148 0 20 Oct 2020
Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation Tianlu Wang Xi Victoria Lin Nazneen Rajani Bryan McCann Vicente Ordonez Caimng Xiong CVBM 94 49 0 03 May 2020
The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives Elena Voita Rico Sennrich Ivan Titov 177 166 0 03 Sep 2019