arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.08779cs.CL
收藏

迈向摘要候选融合

Towards Summary Candidates Fusion

Nanyang Technological University(南洋理工大学);Salesforce Research(Salesforce研究院)

Mathieu Ravaut, Shafiq Joty, Nancy F. Chen

AI总结:

本文提出SummaFusion方法,通过融合多个摘要候选生成更优的第二阶段抽象式摘要,在多个数据集上提升ROUGE分数,并在少样本场景下取得新最优结果。

摘要:

针对抽象式摘要微调的序列到序列深度神经模型,在具有足够人工标注的数据集上可以取得优异性能。然而,研究表明它们尚未充分发挥潜力,最佳束搜索输出与理想束之间存在较大差距。最近,研究者提出了重排序方法,通过学习选择更好的摘要候选。但是,这类方法受限于第一阶段候选所捕捉到的摘要质量方面。为突破这一限制,我们提出了一种用于第二阶段抽象式摘要的新范式,称为SummaFusion,它融合多个摘要候选以生成新颖的抽象式第二阶段摘要。我们的方法在多个摘要数据集上表现良好,同时提升了融合摘要的ROUGE分数和定性属性。当待融合的候选质量较差时,该方法尤其有效,例如在少样本设置中,我们取得了新的最优结果。我们将在https://github.com/ntunlp/SummaFusion/公开代码和检查点。

英文摘要:

Sequence-to-sequence deep neural models fine-tuned for abstractive summarization can achieve great performance on datasets with enough human annotations. Yet, it has been shown that they have not reached their full potential, with a wide gap between the top beam search output and the oracle beam. Recently, re-ranking methods have been proposed, to learn to select a better summary candidate. However, such methods are limited by the summary quality aspects captured by the first-stage candidates. To bypass this limitation, we propose a new paradigm in second-stage abstractive summarization called SummaFusion that fuses several summary candidates to produce a novel abstractive second-stage summary. Our method works well on several summarization datasets, improving both the ROUGE scores and qualitative properties of fused summaries. It is especially good when the candidates to fuse are worse, such as in the few-shot setup where we set a new state-of-the-art. We will make our code and checkpoints available at https://github.com/ntunlp/SummaFusion/.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑