Articlegreen2020

On Measuring and Mitigating Biased Inferences of Word Embeddings

Sunipa Dev · Tao Li · Jeff M. Phillips · Vivek Srikumar

101 citations0/0 files storedAAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Ethics and Social Impacts of AI Topic Modeling Hate Speech and Cyberbullying Detection

Abstract

Word embeddings carry stereotypical connotations from the text they are trained on, which can lead to invalid inferences in downstream models that rely on them. We use this observation to design a mechanism for measuring stereotypes using the task of natural language inference. We demonstrate a reduction in invalid inferences via bias mitigation strategies on static word embeddings (GloVe). Further, we show that for gender bias, these techniques extend to contextualized embeddings when applied selectively only to the static components of contextualized embeddings (ELMo, BERT).

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 101 citations exist upstream.

References

2017Semantics derived automatically from language corpora contain human-like biases 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints 2019Gender Bias in Contextualized Word Embeddings 2019Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them

Cited by

2021Sustainable Modular Debiasing of Language Models 2024Believing Anthropomorphism: Examining the Role of Anthropomorphic Cues on Trust in Large Language Models 2024“They only care to show us the wheelchair”: disability representation in text-to-image AI models 2020UNQOVERing Stereotyping Biases via Underspecified Questions 2022You reap what you sow: On the Challenges of Bias Evaluation Under Multilingual Settings 2022Measuring Fairness with Biased Rulers: A Comparative Study on Bias Metrics for Pre-trained Language Models 2023Fairness in Deep Learning: A Survey on Vision and Language Research 2023

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.