Abstractive summarization for long-document or multi-document remains challenging for the Seq2Seq architecture, as Seq2Seq is not good at analyzing long-distance relations in text.
Most previous seq2seq summarization systems purely depend on the source text to generate summaries, which tends to work unstably.
Ranked #17 on Text Summarization on GigaWord
While previous abstractive summarization approaches usually focus on the improvement of informativeness, we argue that faithfulness is also a vital prerequisite for a practical abstractive summarization system.
Ranked #16 on Text Summarization on GigaWord
Developed so far, multi-document summarization has reached its bottleneck due to the lack of sufficient training data and diverse categories of documents.
In this paper, we develop a novel Seq2Seq model to fuse a copying decoder and a restricted generative decoder.
Both informativeness and readability of the collected summaries are verified by manual judgment.
However, according to our quantitative analysis, none of the existing summarization models can always produce high-quality summaries for different document sets, and even a summarization model with good overall performance may produce low-quality summaries for some document sets.