Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893425640> ?p ?o ?g. }
- W2893425640 endingPage "186" @default.
- W2893425640 startingPage "183" @default.
- W2893425640 abstract "Artificial intelligence and machine learning are in a period of astounding growth. However, there are concerns that these technologies may be used, either with or without intention, to perpetuate the prejudice and unfairness that unfortunately characterizes many human institutions. Here we show for the first time that human-like semantic biases result from the application of standard machine learning to ordinary language---the same sort of language humans are exposed to every day. We replicate a spectrum of standard human biases as exposed by the Implicit Association Test and other well-known psychological studies. We replicate these using a widely used, purely statistical machine-learning model---namely, the GloVe word embedding---trained on a corpus of text from the Web. Our results indicate that language itself contains recoverable and accurate imprints of our historic biases, whether these are morally neutral as towards insects or flowers, problematic as towards race or gender, or even simply veridical, reflecting the {em status quo} for the distribution of gender with respect to careers or first names. These regularities are captured by machine learning along with the rest of semantics. In addition to our empirical findings concerning language, we also contribute new methods for evaluating bias in text, the Word Embedding Association Test (WEAT) and the Word Embedding Factual Association Test (WEFAT). Our results have implications not only for AI and machine learning, but also for the fields of psychology, sociology, and human ethics, since they raise the possibility that mere exposure to everyday language can account for the biases we replicate here." @default.
- W2893425640 created "2018-10-05" @default.
- W2893425640 creator A5021658557 @default.
- W2893425640 creator A5037130457 @default.
- W2893425640 creator A5058102069 @default.
- W2893425640 date "2017-04-14" @default.
- W2893425640 modified "2023-10-16" @default.
- W2893425640 title "Semantics derived automatically from language corpora contain human-like biases" @default.
- W2893425640 cites W1662133657 @default.
- W2893425640 cites W1978400666 @default.
- W2893425640 cites W1994939056 @default.
- W2893425640 cites W2005245615 @default.
- W2893425640 cites W2014352947 @default.
- W2893425640 cites W2066255970 @default.
- W2893425640 cites W2100960835 @default.
- W2893425640 cites W2102225743 @default.
- W2893425640 cites W2108193005 @default.
- W2893425640 cites W2149280200 @default.
- W2893425640 cites W2279213940 @default.
- W2893425640 cites W3123223998 @default.
- W2893425640 cites W4231165370 @default.
- W2893425640 cites W4253260352 @default.
- W2893425640 doi "https://doi.org/10.1126/science.aal4230" @default.
- W2893425640 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/28408601" @default.
- W2893425640 hasPublicationYear "2017" @default.
- W2893425640 type Work @default.
- W2893425640 sameAs 2893425640 @default.
- W2893425640 citedByCount "1384" @default.
- W2893425640 countsByYear W28934256402017 @default.
- W2893425640 countsByYear W28934256402018 @default.
- W2893425640 countsByYear W28934256402019 @default.
- W2893425640 countsByYear W28934256402020 @default.
- W2893425640 countsByYear W28934256402021 @default.
- W2893425640 countsByYear W28934256402022 @default.
- W2893425640 countsByYear W28934256402023 @default.
- W2893425640 crossrefType "journal-article" @default.
- W2893425640 hasAuthorship W2893425640A5021658557 @default.
- W2893425640 hasAuthorship W2893425640A5037130457 @default.
- W2893425640 hasAuthorship W2893425640A5058102069 @default.
- W2893425640 hasBestOaLocation W28934256402 @default.
- W2893425640 hasConcept C105795698 @default.
- W2893425640 hasConcept C107062074 @default.
- W2893425640 hasConcept C138885662 @default.
- W2893425640 hasConcept C151730666 @default.
- W2893425640 hasConcept C154945302 @default.
- W2893425640 hasConcept C15744967 @default.
- W2893425640 hasConcept C180747234 @default.
- W2893425640 hasConcept C184337299 @default.
- W2893425640 hasConcept C199360897 @default.
- W2893425640 hasConcept C204321447 @default.
- W2893425640 hasConcept C23123220 @default.
- W2893425640 hasConcept C2777267654 @default.
- W2893425640 hasConcept C2777462759 @default.
- W2893425640 hasConcept C2781162219 @default.
- W2893425640 hasConcept C33923547 @default.
- W2893425640 hasConcept C41008148 @default.
- W2893425640 hasConcept C41608201 @default.
- W2893425640 hasConcept C41895202 @default.
- W2893425640 hasConcept C77805123 @default.
- W2893425640 hasConcept C86803240 @default.
- W2893425640 hasConcept C88548561 @default.
- W2893425640 hasConcept C90805587 @default.
- W2893425640 hasConceptScore W2893425640C105795698 @default.
- W2893425640 hasConceptScore W2893425640C107062074 @default.
- W2893425640 hasConceptScore W2893425640C138885662 @default.
- W2893425640 hasConceptScore W2893425640C151730666 @default.
- W2893425640 hasConceptScore W2893425640C154945302 @default.
- W2893425640 hasConceptScore W2893425640C15744967 @default.
- W2893425640 hasConceptScore W2893425640C180747234 @default.
- W2893425640 hasConceptScore W2893425640C184337299 @default.
- W2893425640 hasConceptScore W2893425640C199360897 @default.
- W2893425640 hasConceptScore W2893425640C204321447 @default.
- W2893425640 hasConceptScore W2893425640C23123220 @default.
- W2893425640 hasConceptScore W2893425640C2777267654 @default.
- W2893425640 hasConceptScore W2893425640C2777462759 @default.
- W2893425640 hasConceptScore W2893425640C2781162219 @default.
- W2893425640 hasConceptScore W2893425640C33923547 @default.
- W2893425640 hasConceptScore W2893425640C41008148 @default.
- W2893425640 hasConceptScore W2893425640C41608201 @default.
- W2893425640 hasConceptScore W2893425640C41895202 @default.
- W2893425640 hasConceptScore W2893425640C77805123 @default.
- W2893425640 hasConceptScore W2893425640C86803240 @default.
- W2893425640 hasConceptScore W2893425640C88548561 @default.
- W2893425640 hasConceptScore W2893425640C90805587 @default.
- W2893425640 hasIssue "6334" @default.
- W2893425640 hasLocation W28934256401 @default.
- W2893425640 hasLocation W28934256402 @default.
- W2893425640 hasLocation W28934256403 @default.
- W2893425640 hasLocation W28934256404 @default.
- W2893425640 hasLocation W28934256405 @default.
- W2893425640 hasLocation W28934256406 @default.
- W2893425640 hasOpenAccess W2893425640 @default.
- W2893425640 hasPrimaryLocation W28934256401 @default.
- W2893425640 hasRelatedWork W2335882425 @default.
- W2893425640 hasRelatedWork W2620816324 @default.
- W2893425640 hasRelatedWork W2949267551 @default.
- W2893425640 hasRelatedWork W2993300079 @default.
- W2893425640 hasRelatedWork W2997521053 @default.