A Split-then-Join Approach to Abstractive Summarization for Very Long Documents in a Low Resource Setting
This work addresses the challenge of summarizing very long documents for NLP applications, but it is incremental as it builds on existing BIGBIRD-PEGASUS methods with data augmentation.
The researchers tackled the problem of abstractive summarization for very long documents exceeding 4,096 tokens by proposing a split-then-join approach, which involved fine-tuning the BIGBIRD-PEGASUS model on augmented data from documents over 20,000 tokens to improve performance in low-resource settings.
$\texttt{BIGBIRD-PEGASUS}$ model achieves $\textit{state-of-the-art}$ on abstractive text summarization for long documents. However it's capacity still limited to maximum of $4,096$ tokens, thus caused performance degradation on summarization for very long documents. Common method to deal with the issue is to truncate the documents. In this reasearch, we'll use different approach. We'll use the pretrained $\texttt{BIGBIRD-PEGASUS}$ model by fine tuned the model on other domain dataset. First, we filter out all documents which length less than $20,000$ tokens to focus on very long documents. To prevent domain shifting problem and overfitting on transfer learning due to small dataset, we augment the dataset by splitting document-summary training pair into parts, to fit the document into $4,096$ tokens. Source code available on $\href{https://github.com/lhfazry/SPIN-summ}{https://github.com/lhfazry/SPIN-summ}$.