Show simple item record

dc.contributor.authorIzzidien, Ahmeden
dc.date.accessioned2021-03-05T09:10:04Z
dc.date.available2021-03-05T09:10:04Z
dc.identifier.issn0951-5666
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/318432
dc.description.abstractProgramming artificial intelligence (AI) to make fairness assessments of texts through top-down rules, bottom-up training, or hybrid approaches, has presented the challenge of defining cross-cultural fairness. In this paper a simple method is presented which uses vectors to discover if a verb is unfair (e.g., slur, insult) or fair (e.g., thank, appreciate). It uses already existing relational social ontologies inherent in Word Embeddings and thus requires no training. The plausibility of the approach rests on two premises. That individuals consider fair acts those that they would be willing to accept if done to themselves. Secondly, that such a construal is ontologically reflected in Word Embeddings, by virtue of their ability to reflect the dimensions of such a perception. These dimensions being: responsibility vs. irresponsibility, gain vs. loss, reward vs. sanction, joy vs. pain, all as a single vector (FairVec). The paper finds it possible to quantify and qualify a verb as fair or unfair by calculating the cosine similarity of the said verb’s embedding vector against FairVec - which represents the above dimensions. We apply this to Glove and Word2Vec embeddings. Testing on a list of verbs produces an F1 score of 95.7, which is improved to 97.0. Lastly, a demonstration of the method’s applicability to sentence measurement is carried out.
dc.description.sponsorshipThis research was funded by the European Union’s Horizon 2020 research and innovation programme under the Next Generation Internet TRUST grant agreement no. 825618.
dc.publisherSpringer
dc.rightsAttribution 4.0 International (CC BY)
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectFairnessen
dc.subjectMeaningen
dc.subjectMoralityen
dc.subjectLegal Philosophyen
dc.subjectResponsibilityen
dc.subjectPolicyen
dc.titleWord vector embeddings hold social ontological relations capable of reflecting meaningful fairness assessmentsen
dc.typeArticle
prism.publicationNameAI and Society: the journal of human-centered systems and machine intelligenceen
dc.identifier.doi10.17863/CAM.65544
dcterms.dateAccepted2021-02-18en
rioxxterms.versionofrecord10.1007/s00146-021-01167-3en
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2021-02-18en
dc.contributor.orcidIzzidien, Ahmed [0000-0002-0929-8064]
dc.identifier.eissn1435-5655
rioxxterms.typeJournal Article/Reviewen
cam.issuedOnline2021-03-24en
cam.orpheus.successMon Mar 29 07:30:44 BST 2021 - Embargo updated*
cam.orpheus.counter3*
rioxxterms.freetoread.startdate2100-01-01


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International (CC BY)
Except where otherwise noted, this item's licence is described as Attribution 4.0 International (CC BY)