On Measuring and Mitigating Biased Inferences of Word Embeddings
Year: 2020
Type: conference-paper
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).
Institution: University of Utah
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
Funder: National Science Foundation
Awards: CIF21 DIBBs: STORM: Spatio-Temporal Online Reasoning and Management of Large Data, CAREER: Foundations for Geometric Analysis of Noisy Data, SaTC: CORE: Medium: Large-Scale Data Driven Anomaly Detection and Diagnosis from System Logs, III: Small: Persistent Data Summaries: Temporal Analytics on Big Data Histories, TWC: Medium: Collaborative: Seal: Secure Engine for AnaLytics - From Secure Similarity Search to Secure Data Analytics, Technology Facilitated Training for Mental Health Counseling, NeTS: Medium: Collaborative Research: Detecting and Localizing Spectrum Offenders Using Crowdsourcing
OpenAlex ID: W2969426522