Hate Speech Classifiers Learn Normative Social Stereotypes TACL

Aida Mostafazadeh Davani | Mohammad Atari | Brendan Kennedy | Morteza Dehghani |

Social-Group-Agnostic Bias Mitigation via the Stereotype Content Model ACL

Ali Omrani | Alireza Salkhordeh Ziabari | Charles Yu | Preni Golazizian | Brendan Kennedy | Mohammad Atari | Heng Ji | Morteza Dehghani |

On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning NAACL

Xisen Jin | Francesco Barbieri | Brendan Kennedy | Aida Mostafazadeh Davani | Leonardo Neves | Xiang Ren |

Improving Counterfactual Generation for Fair Hate Speech Detection ACL IJCNLP WOAH

Aida Mostafazadeh Davani | Ali Omrani | Brendan Kennedy | Mohammad Atari | Xiang Ren | Morteza Dehghani |

Contextualizing Hate Speech Classifiers with Post-hoc Explanation ACL

Brendan Kennedy | Xisen Jin | Aida Mostafazadeh Davani | Morteza Dehghani | Xiang Ren |

Reporting the Unreported: Event Extraction for Analyzing the Local Representation of Hate Crimes EMNLP

Aida Mostafazadeh Davani | Leigh Yeh | Mohammad Atari | Brendan Kennedy | Gwenyth Portillo Wightman | Elaine Gonzalez | Natalie Delong | Rhea Bhatia | Arineh Mirinjian | Xiang Ren | Morteza Dehghani |

Modeling performance differences on cognitive tests using LSTMs and skip-thought vectors trained on reported media consumption. NAACL WS

Maury Courtland | Aida Davani | Melissa Reyes | Leigh Yeh | Jun Leung | Brendan Kennedy | Morteza Dehghani | Jason Zevin |