Get To The Point: Summarization with Pointer-Generator Networks
This addresses the challenge of generating accurate and non-repetitive summaries for text summarization tasks, representing a strong incremental advance in the field.
The paper tackled the problem of factual inaccuracies and repetition in neural abstractive summarization by proposing a hybrid pointer-generator network with coverage, resulting in at least 2 ROUGE points improvement over the state-of-the-art on the CNN/Daily Mail dataset.
Neural sequence-to-sequence models have provided a viable new approach for abstractive text summarization (meaning they are not restricted to simply selecting and rearranging passages from the original text). However, these models have two shortcomings: they are liable to reproduce factual details inaccurately, and they tend to repeat themselves. In this work we propose a novel architecture that augments the standard sequence-to-sequence attentional model in two orthogonal ways. First, we use a hybrid pointer-generator network that can copy words from the source text via pointing, which aids accurate reproduction of information, while retaining the ability to produce novel words through the generator. Second, we use coverage to keep track of what has been summarized, which discourages repetition. We apply our model to the CNN / Daily Mail summarization task, outperforming the current abstractive state-of-the-art by at least 2 ROUGE points.