Summary Refinement through Denoising
This work addresses redundancy issues in text summarization for NLP applications, but it is incremental as it builds on existing summarization methods.
The paper tackled the problem of information redundancy in text summarization by training text-to-text rewriting models to correct errors, resulting in metric improvements and reduced redundancy when applied to extractive and abstractive summarization baselines.
We propose a simple method for post-processing the outputs of a text summarization system in order to refine its overall quality. Our approach is to train text-to-text rewriting models to correct information redundancy errors that may arise during summarization. We train on synthetically generated noisy summaries, testing three different types of noise that introduce out-of-context information within each summary. When applied on top of extractive and abstractive summarization baselines, our summary denoising models yield metric improvements while reducing redundancy.