Picture for Björn Ross

Björn Ross

Explainability and Hate Speech: Structured Explanations Make Social Media Moderators Faster

Add code
Jun 06, 2024
Viaarxiv icon

Detecting Statements in Text: A Domain-Agnostic Few-Shot Solution

Add code
May 09, 2024
Viaarxiv icon

Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models

Add code
May 26, 2023
Figure 1 for Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models
Figure 2 for Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models
Figure 3 for Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models
Figure 4 for Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models
Viaarxiv icon

Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis

Add code
May 22, 2023
Figure 1 for Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis
Figure 2 for Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis
Figure 3 for Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis
Figure 4 for Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis
Viaarxiv icon

A Robust Bias Mitigation Procedure Based on the Stereotype Content Model

Add code
Oct 26, 2022
Figure 1 for A Robust Bias Mitigation Procedure Based on the Stereotype Content Model
Figure 2 for A Robust Bias Mitigation Procedure Based on the Stereotype Content Model
Figure 3 for A Robust Bias Mitigation Procedure Based on the Stereotype Content Model
Viaarxiv icon

Explainable Abuse Detection as Intent Classification and Slot Filling

Add code
Oct 06, 2022
Figure 1 for Explainable Abuse Detection as Intent Classification and Slot Filling
Figure 2 for Explainable Abuse Detection as Intent Classification and Slot Filling
Figure 3 for Explainable Abuse Detection as Intent Classification and Slot Filling
Figure 4 for Explainable Abuse Detection as Intent Classification and Slot Filling
Viaarxiv icon

Towards Successful Collaboration: Design Guidelines for AI-based Services enriching Information Systems in Organisations

Dec 02, 2019
Viaarxiv icon

Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis

Add code
Jan 27, 2017
Figure 1 for Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis
Figure 2 for Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis
Viaarxiv icon