Controlling Decoding for More Abstractive Summaries with Copy-Based Networks
This addresses the issue of over-copying in abstractive summarization for NLP researchers, offering an incremental improvement with a practical baseline.
The paper tackles the problem of neural abstractive summarization systems excessively copying from source text, verifying this behavior in a pointer-generator network and proposing a simple baseline method to control copying without retraining. The method reduces n-gram overlap substantially while maintaining ROUGE scores within 2 points of the original model.
Attention-based neural abstractive summarization systems equipped with copy mechanisms have shown promising results. Despite this success, it has been noticed that such a system generates a summary by mostly, if not entirely, copying over phrases, sentences, and sometimes multiple consecutive sentences from an input paragraph, effectively performing extractive summarization. In this paper, we verify this behavior using the latest neural abstractive summarization system - a pointer-generator network. We propose a simple baseline method that allows us to control the amount of copying without retraining. Experiments indicate that the method provides a strong baseline for abstractive systems looking to obtain high ROUGE scores while minimizing overlap with the source article, substantially reducing the n-gram overlap with the original article while keeping within 2 points of the original model's ROUGE score.