Classifiers tend to learn a false causal relationship between an
over-re...
The criminalization of poverty has been widely denounced as a collective...
As text-to-image systems continue to grow in popularity with the general...
Previous works on the fairness of toxic language classifiers compare the...
Motivations for methods in explainable artificial intelligence (XAI) oft...
In an effort to guarantee that machine learning model outputs conform wi...
We present a novel feature attribution method for explaining text
classi...
Robustness of machine learning models on ever-changing real-world data i...
Stereotypical language expresses widely-held beliefs about different soc...
The pervasiveness of abusive content on the internet can lead to severe
...
To support safety and inclusion in online communications, significant ef...
NLP research has attained high performances in abusive language detectio...
The state of being alone can have a substantial impact on our lives, tho...
In this paper, we describe the 2015 iteration of the SemEval shared task...
Our team, NRC-Canada, participated in two shared tasks at the AMIA-2017
...
In this paper, we explore sentiment composition in phrases that have at ...
Automatic machine learning systems can inadvertently accentuate and
perp...
Negators, modals, and degree adverbs can significantly affect the sentim...
Rating scales are a widely used method for data annotation; however, the...
Access to word-sentiment associations is useful for many applications,
i...
We can often detect from a person's utterances whether he/she is in favo...