• Computer Science
  • Published in ArXiv 2019

Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview

@article{Shah2019PredictiveBI,
  title={Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview},
  author={Deven Shah and H. Andrew Schwartz and Dirk Hovy},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.11078}
}
An increasing number of works in natural language processing have addressed the effect of bias on the predicted outcomes, introducing mitigation techniques that act on different parts of the standard NLP pipeline (data and models). However, these works have been conducted in isolation, without a unifying framework to organize efforts within the field. This leads to repetitive approaches, and puts an undue focus on the effects of bias, rather than on their origins. Research focused on bias… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 77 REFERENCES

Measuring Bias in Contextualized Word Representations

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Data Statements for Natural Language Processing: Toward Mitigating System Bias and Enabling Better Science

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

On the (im)possibility of fairness

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Situation Recognition: Visual Semantic Role Labeling for Image Understanding

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Reducing sampling bias in social media data for county health inference

  • Aron Culotta.
  • Joint Statistical Meetings Proceedings, pages 1–12.
  • 2014
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL