Unsupervised Multi-document Summarization with Holistic Inference
Unsupervised Multi-document Summarization with Holistic Inference
复制标题
DOI：
10.48550/arxiv.2309.04087
复制
发表时间：
2023-09
期刊：
影响因子：
--
通讯作者：
Haopeng Zhang;Sangwoo Cho;Kaiqiang Song;Xiaoyang Wang;Hongwei Wang;Jiawei Zhang;Dong Yu
中科院分区：
文献类型：
--
作者：
Haopeng Zhang;Sangwoo Cho;Kaiqiang Song;Xiaoyang Wang;Hongwei Wang;Jiawei Zhang;Dong Yu
多文档摘要旨在从同一主题的文档集合中获取核心信息。提出了一种新的无监督多文档抽取摘要整体框架。我们的方法结合了与整体测量相关联的整体波束搜索推理方法，称为子集代表性索引（子集Representative Index， SRI）。SRI平衡了源文档中句子子集的重要性和多样性，可以以无监督和自适应的方式进行计算。为了证明我们方法的有效性，我们在无监督和自适应设置下对小型和大型多文档摘要数据集进行了广泛的实验。所提出的方法在很大程度上优于强基线，正如所得到的ROUGE分数和多样性度量所表明的那样。我们的研究结果还表明，多样性对于提高多文档摘要性能至关重要。
Multi-document summarization aims to obtain core information from a collection of documents written on the same topic. This paper proposes a new holistic framework for unsupervised multi-document extractive summarization. Our method incorporates the holistic beam search inference method associated with the holistic measurements, named Subset Representative Index (SRI). SRI balances the importance and diversity of a subset of sentences from the source documents and can be calculated in unsupervised and adaptive manners. To demonstrate the effectiveness of our method, we conduct extensive experiments on both small and large-scale multi-document summarization datasets under both unsupervised and adaptive settings. The proposed method outperforms strong baselines by a significant margin, as indicated by the resulting ROUGE scores and diversity measures. Our findings also suggest that diversity is essential for improving multi-document summary performance.