Fine-Tuning a Seq2Seq model for sentence fusion in English.
Sentence fusion is the task of joining several independent sentences into a single coherent text. E.g.: the sentences:
Hillary goes to school. Hillary meets her friends at school.
could be fused to
Hillary goes to school and meets her friends.
Currently there is only one model on the hub for sentence fusion as can be seen on the dataset site: discofuse · Datasets at Hugging Face .
The goal of this project is to have the best sentence fusion model for English on the hub.
Model
One use one or multiple of the pretrained T5 models:
Datasets
The Discofuse dataset can be used: discofuse · Datasets at Hugging Face
Available training scripts
As this will be a Seq2Seq model, the run_summarization_flax.py script can be used for training.
(Optional) Desired project outcome
The desired outcome is to have a sentence fusion model for the English language. This can be showcased directly on the hub or with a streamlit or gradio app.
(Optional) Challenges
Beating the existing model will be the most challenging part.