In this paper, we describe the system proposed by the MilaNLP team for the Multimedia Automatic Misogyny Identification (MAMI) challenge.
In this paper, we provide the first benchmark study of interpretability approaches for hate speech detection.
In MT, this might lead to misgendered translations, resulting, among other harms, in the perpetuation of stereotypes and prejudices.
Existing work focuses on a few spoken language understanding (SLU) tasks, and explanations are difficult to interpret for most users.
Training large language models to follow instructions makes them perform better on a wide range of tasks, generally becoming more helpful.
Regularized models produce better counter narratives than state-of-the-art approaches in most cases, both in terms of automatic metrics and human evaluation, especially when hateful targets are not present in the training data.
In this paper, we introduce a new test suite called XSTest to identify such eXaggerated Safety behaviours in a systematic way.
Recent large-scale Spoken Language Understanding datasets focus predominantly on English and do not account for language-specific phenomena such as particular phonemes or words in different lects.
Recommender Systems today are still mostly evaluated in terms of accuracy, with other aspects beyond the immediate relevance of recommendations, such as diversity, long-term user retention and fairness, often taking a back seat.
Consequently, we should continuously update our models with new data to expose them to new events and facts.
With ferret, users can visualize and compare transformers-based models output explanations using state-of-the-art XAI methods on any free-text or existing XAI corpora.
Much of the complexity of Recommender Systems (RSs) comes from the fact that they are used as part of more complex applications and affect user experience through a varied range of user interfaces.
The steady rise of online shopping goes hand in hand with the development of increasingly complex ML and NLP models.
EAR also reveals overfitting terms, i. e., terms most likely to induce bias, to help identify their effect on the model, task, and predictions.
CLIP (Contrastive Language-Image Pre-training) is a very recent multi-modal model that jointly learns representations of images and texts.