Incorporating Question Answering-Based Signals into Abstractive Summarization via Salient Span Selection
This work addresses the challenge of producing more accurate and controllable summaries for natural language processing applications, representing an incremental improvement over existing methods.
The authors tackled the problem of improving abstractive summarization by incorporating question-answering signals to identify salient noun phrases, resulting in models that generate higher-quality summaries than baseline methods on benchmark datasets.
In this work, we propose a method for incorporating question-answering (QA) signals into a summarization model. Our method identifies salient noun phrases (NPs) in the input document by automatically generating wh-questions that are answered by the NPs and automatically determining whether those questions are answered in the gold summaries. This QA-based signal is incorporated into a two-stage summarization model which first marks salient NPs in the input document using a classification model, then conditionally generates a summary. Our experiments demonstrate that the models trained using QA-based supervision generate higher-quality summaries than baseline methods of identifying salient spans on benchmark summarization datasets. Further, we show that the content of the generated summaries can be controlled based on which NPs are marked in the input document. Finally, we propose a method of augmenting the training data so the gold summaries are more consistent with the marked input spans used during training and show how this results in models which learn to better exclude unmarked document content.