This paper presents the MEDIQA-Chat 2023 shared task organized at the ACL-Clinical NLP workshop. The shared task is motivated by the need to develop methods to automatically generate clinical notes from doctor-patient conversations. In this paper, we present our submission for MEDIQA-Chat 2023 Task A: Short Dialogue2Note Summarization. Manual creation of these clinical notes requires extensive human efforts, thus making it a time-consuming and expensive process. To address this, we propose an ensemble-based method over GPT-3, BART, BERT variants, and Rule-based systems to automatically generate clinical notes from these conversations. The proposed system achieves a score of 0.730 and 0.544 for both the sub-tasks on the test set (ranking 8th on the leaderboard for both tasks) and shows better performance compared to a baseline system using BART variants.

This paper describes our system submission Hasyarasa for the SemEval-2020 Task-7: Assessing Humor in Edited News Headlines. This task has two subtasks. The goal of Subtask 1 is to predict the mean funniness of the edited headline given the original and the edited headline. In Subtask 2, given two edits on the original headline, the goal is to predict the funnier of the two. We observed that the departure from expected state/ actions of situations/ individuals is the cause of humor in the edited headlines. We propose two novel features: Contextual Semantic Distance and Contextual Neighborhood Distance to estimate this departure and thus capture the contextual absurdity and hence the humor in the edited headlines. We have used these features together with a Bi-LSTM Attention based model and have achieved 0.53310 RMSE for Subtask 1 and 60.19% accuracy for Subtask 2.