In this paper, we highlight our approach for the “WASSA 2023 Shared-Task 1: Empathy Detection and Emotion Classification”. By accurately identifying emotions from textual sources of data, deep learning models can be trained to understand and interpret human emotions more effectively. The classification of emotions facilitates the creation of more emotionally intelligent systems that can better understand and respond to human emotions. We compared multiple transformer-based models for multi-label classification. Ensembling and oversampling were used to improve the performance of the system. A threshold-based voting mechanism performed on three models (Longformer, BERT, BigBird) yields the highest overall macro F1-score of 0.6605.

In this paper, we elaborate on our approach for the shared task 1A issued by BioNLP Workshop 2023 titled Problem List Summarization. With an increase in the digitization of health records, a need arises for quick and precise summarization of large amounts of records. With the help of summarization, medical professionals can sieve through multiple records in a short span of time without overlooking any crucial point. We use abstractive text summarization for this task and experiment with multiple state-of-the-art models like Pegasus, BART, and T5, along with various pre-processing and data augmentation techniques to generate summaries from patients’ progress notes. For this task, the metric used was the ROUGE-L score. From our experiments, we conclude that Pegasus is the best-performing model on the dataset, achieving a ROUGE-L F1 score of 0.2744 on the test dataset (3rd rank on the leaderboard).