research
∙
02/22/2022
A New Generation of Perspective API: Efficient Multilingual Character-level Transformers
On the world wide web, toxic content detectors are a crucial line of def...
share
research
∙
11/19/2021
Toxicity Detection can be Sensitive to the Conversational Context
User posts whose perceived toxicity depends on the conversational contex...
research
∙
02/01/2021
Civil Rephrases Of Toxic Texts With Self-Supervised Transformers
Platforms that support online commentary, from social networks to news s...
research
∙
10/14/2020
Six Attributes of Unhealthy Conversation
We present a new dataset of approximately 44000 comments labeled by crow...
research
∙
06/01/2020
Toxicity Detection: Does Context Really Matter?
Moderation is crucial to promoting healthy on-line discussions. Although...
research
∙
04/11/2020
Classifying Constructive Comments
We introduce the Constructive Comments Corpus (C3), comprised of 12,000 ...
research
∙
03/11/2019
Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification
Unintended bias in Machine Learning can manifest as systemic differences...
research
∙
03/05/2019