Word vector embeddings hold social ontological relations capable of reflecting meaningful fairness assessments
Authors
Izzidien, A
Publication Date
2022-03Journal Title
AI and Society: the journal of human-centered systems and machine intelligence
ISSN
0951-5666
Publisher
Springer
Volume
37
Issue
1
Pages
299-318
Language
en
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Izzidien, A. (2022). Word vector embeddings hold social ontological relations capable of reflecting meaningful fairness assessments. AI and Society: the journal of human-centered systems and machine intelligence, 37 (1), 299-318. https://doi.org/10.1007/s00146-021-01167-3
Abstract
Programming 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.
Keywords
Open Forum, Fairness, Word Meaning, Morality, Legal Philosophy, Responsibility, Policy
Sponsorship
This research was funded by the European Union’s Horizon 2020 research and innovation programme under the Next Generation Internet TRUST grant agreement no. 825618.
Identifiers
s00146-021-01167-3, 1167
External DOI: https://doi.org/10.1007/s00146-021-01167-3
This record's URL: https://www.repository.cam.ac.uk/handle/1810/334051
Rights
Licence:
http://creativecommons.org/licenses/by/4.0/
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.
Recommended or similar items
The current recommendation prototype on the Apollo Repository will be turned off on 03 February 2023. Although the pilot has been fruitful for both parties, the service provider IKVA is focusing on horizon scanning products and so the recommender service can no longer be supported. We recognise the importance of recommender services in supporting research discovery and are evaluating offerings from other service providers. If you would like to offer feedback on this decision please contact us on: support@repository.cam.ac.uk