Teaching AI when to care about gender

Journal Article · Mon Aug 29 00:00:00 EDT 2022 · Code4Lib Journal

OSTI ID:1885750

Powell, James ^[1]; Sentz, Kari ^[1]; Moyer, Elizabeth Chase ^[1]; Klein, Martin ^[1]

---

1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Natural Language Processing (NLP) is a branch of Artificial Intelligence (AI) concerned with solving language tasks by modeling large amounts of textual data. Some NLP techniques use word embeddings which are semantic models where machine learning (ML) is used to learn to cluster semantically related words by learning about word co-occurrences in the original training text. Unfortunately, these models tend to reflect or even exaggerate biases that are present in the training corpus. Here we describe the Word Embedding Navigator (WEN), which is a tool for exploring word embedding models. We examine a specific potential use case for this tool: interactive discovery and neutralization of gender bias in word embedding models, and compare this human-in-the-loop approach to reducing bias in word embeddings with a debiasing post-processing technique.

• Research Organization: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
• Sponsoring Organization: USDOE
• Grant/Contract Number: 89233218CNA000001
• OSTI ID: 1885750
• Report Number(s): LA-UR-22-27833
• Journal Information: Code4Lib Journal, Journal Name: Code4Lib Journal Vol. 54; ISSN 1940-5758
• Publisher: code4lib.org
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING
information science
natural language processing machine learning word embeddings
natural language processing machine learning word embeddings bias