Given a sample of size $N$, it is often useful to select a subsample of smaller size $n

University of New Brunswick (UNB) alumnus Dick Carpenter (BA '72) and the McKenna Institute are pleased to announce a gift of $2.5 million to advance the development of artificial intelligence (AI) and data science at UNB. AI and data science have become essential elements in the creation of effective digital products and services. AI depends on large data sets for developing reliable predictive models and data science relies on AI algorithms to extract meaningful features from data sets. This interdependence has resulted in AI and data science becoming increasingly intertwined and dependent upon advances in math, computer science and software engineering. This gift will support the development of interdisciplinary AI and data science research across UNB's faculties and campuses. It was secured through the ambassadorship of UNB alumnus and former New Brunswick premier The Hon. "We tend to think of AI in terms of social media algorithms," said Dr. Paul J. Mazerolle, UNB's president and vice-chancellor.

The universal-set naive Bayes classifier (UNB)~\cite{Komiya:13}, defined using likelihood ratios (LRs), was proposed to address imbalanced classification problems. However, the LR estimator used in the UNB overestimates LRs for low-frequency data, degrading the classification performance. Our previous study~\cite{Kikuchi:19} proposed an effective LR estimator even for low-frequency data. This estimator uses regularization to suppress the overestimation, but we did not consider imbalanced data. In this paper, we integrated the estimator with the UNB. Our experiments with imbalanced data showed that our proposed classifier effectively adjusts the classification scores according to the class balance using regularization parameters and improves the classification performance.

Patronizing and condescending language (PCL) has a large harmful impact and is difficult to detect, both for human judges and existing NLP systems. At SemEval-2022 Task 4, we propose a novel Transformer-based model and its ensembles to accurately understand such language context for PCL detection. To facilitate comprehension of the subtle and subjective nature of PCL, two fine-tuning strategies are applied to capture discriminative features from diverse linguistic behaviour and categorical distribution. The system achieves remarkable results on the official ranking, including 1st in Subtask 1 and 5th in Subtask 2. Extensive experiments on the task demonstrate the effectiveness of our system and its strategies.