The manifestation and effect of bias in news reporting have been central...
Despite increasing interest in the automatic detection of media frames i...
We present a large, multilingual study into how vision constrains lingui...
Gender discrimination in hiring is a pertinent and persistent bias in
so...
Mitigating bias in training on biased datasets is an important open prob...
Recent advances in self-supervised modeling of text and images open new
...
Real-world datasets often encode stereotypes and societal biases. Such b...
This paper presents fairlib, an open-source framework for assessing and
...
Providing technologies to communities or domains where training data is
...
Trained classification models can unintentionally lead to biased
represe...
Class imbalance is a common challenge in many NLP tasks, and has clear
c...
Bias is pervasive in NLP models, motivating the development of automatic...
Humans use countless basic, shared facts about the world to efficiently
...
Understanding how news media frame political issues is important due to ...
Cross-lingual transfer is a leading technique for parsing low-resource
l...
Most general-purpose extractive summarization models are trained on news...
The meaning of a word often varies depending on its usage in different
d...
We present a system for answering questions based on the full text of bo...
Categories such as animal or furniture are acquired at an early age and ...
In this paper we argue that crime drama exemplified in television progra...
The impressive ability of children to acquire language is a widely studi...