Incident 12: Biais courants des plongements vectoriels
Description: Des chercheurs de l'Université de Boston et de Microsoft Research, en Nouvelle-Angleterre, ont démontré un biais de genre dans les techniques les plus courantes utilisées pour intégrer des mots dans le traitement du langage naturel (TAL).
Entités
Voir toutes les entitésAlleged: Microsoft Research , Boston University et Google developed an AI system deployed by Microsoft Research et Boston University, which harmed Women et Minority Groups.
Classifications de taxonomie CSETv1
Détails de la taxonomieIncident Number
The number of the incident in the AI Incident Database.
12
Classifications de taxonomie CSETv0
Détails de la taxonomiePublic Sector Deployment
"Yes" if the AI system(s) involved in the accident were being used by the public sector or for the administration of public goods (for example, public transportation). "No" if the system(s) were being used in the private sector or for commercial purposes (for example, a ride-sharing company), on the other.
No
Lives Lost
Were human lives lost as a result of the incident?
No
Intent
Was the incident an accident, intentional, or is the intent unclear?
Unclear
Near Miss
Was harm caused, or was it a near miss?
Unclear/unknown
Ending Date
The date the incident ended.
2016-01-01T00:00:00.000Z
Beginning Date
The date the incident began.
2016-01-01T00:00:00.000Z
Risk Subdomain
A further 23 subdomains create an accessible and understandable classification of hazards and harms associated with AI
1.1. Unfair discrimination and misrepresentation
Risk Domain
The Domain Taxonomy of AI Risks classifies risks into seven AI risk domains: (1) Discrimination & toxicity, (2) Privacy & security, (3) Misinformation, (4) Malicious actors & misuse, (5) Human-computer interaction, (6) Socioeconomic & environmental harms, and (7) AI system safety, failures & limitations.
- Discrimination and Toxicity
Entity
Which, if any, entity is presented as the main cause of the risk
AI
Timing
The stage in the AI lifecycle at which the risk is presented as occurring
Post-deployment
Intent
Whether the risk is presented as occurring as an expected or unexpected outcome from pursuing a goal
Unintentional
Rapports d'incidents
Chronologie du rapport
L'application aveugle de l'apprentissage automatique risque d'amplifier les biais présents dans les données. Nous sommes confrontés à un tel danger avec l'incorporation de mots, un cadre populaire pour représenter les données textuelles sou…
Variantes
Une "Variante" est un incident de l'IA similaire à un cas connu—il a les mêmes causes, les mêmes dommages et le même système intelligent. Plutôt que de l'énumérer séparément, nous l'incluons sous le premier incident signalé. Contrairement aux autres incidents, les variantes n'ont pas besoin d'avoir été signalées en dehors de la base de données des incidents. En savoir plus sur le document de recherche.
Vous avez vu quelque chose de similaire ?
Incidents similaires
Did our AI mess up? Flag the unrelated incidents
:format(webp)/cdn.vox-cdn.com/uploads/chorus_image/image/66547041/dseifert_191123_3810_0011.0.jpg)
Incidents similaires
Did our AI mess up? Flag the unrelated incidents