SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.09369 · 2019

On Measuring and Mitigating Biased Inferences of Word Embeddings

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1908.09369")
get_code_for_paper("1908.09369")
have("1908.09369")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1908.09369.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1908.09369.svg)](https://syntology.ai/paper/1908.09369)

Connect an agent — have() is free.