This repository explores enhancing dialogue summarization with commonsense knowledge through the SICK framework, evaluating models on dialogue datasets to assess commonsense's impact on summarization quality.

For this project, I fine-tuned two separate models for three tasks: document summarization, dialogue summarization and text classification

Instruction fine tuning BART for Dialogue Summarization | IT4772E | NLP Project 20232

A dataset focused on summarization of dialogs, which represents the rich domain of Twitter customer care conversations.

Fine Tuning pegasus and flan-t5 pre-trained language model on dialogsum datasets for conversation summarization to to optimize context window in RAG-LLMs

Dialogue Summarization application hosted using AWS and CICD deployment with docker and FASTAPI. Model card created in HuggingFace and a deployed on HuggingFace Spaces.

[EMNLP 2023] FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization. Support BART, PEGASUS, T5, mT5, BioBART, etc.

Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation

EMNLP 2022: ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization

MEDIQA-Chat Shared Tasks @ ACL-ClinicalNLP 2023

Code and dataset for our Bioinformatics 2022 paper: "A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets"

Small finetuned LLMs for a diverse set of useful tasks