论文标题
事实级的提取性摘要用伯特上的层次图形掩码
Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT
论文作者
论文摘要
大多数当前的提取性摘要模型通过选择显着句子来生成摘要。但是，句子水平的提取性摘要的问题之一是，人类编写的金摘要与Oracle句子标签之间存在差距。在本文中，我们建议提取事实级别的语义单元，以更好地提取摘要。我们还引入了层次结构，该结构将文本信息的粒度多层次结合到模型中。此外，我们使用层次图形掩码将模型与BERT结合在一起。这使我们能够在自然语言理解和结构信息中相结合，而无需增加模型的规模。 CNN/Daliymail数据集的实验表明，我们的模型可实现最新的结果。
Most current extractive summarization models generate summaries by selecting salient sentences. However, one of the problems with sentence-level extractive summarization is that there exists a gap between the human-written gold summary and the oracle sentence labels. In this paper, we propose to extract fact-level semantic units for better extractive summarization. We also introduce a hierarchical structure, which incorporates the multi-level of granularities of the textual information into the model. In addition, we incorporate our model with BERT using a hierarchical graph mask. This allows us to combine BERT's ability in natural language understanding and the structural information without increasing the scale of the model. Experiments on the CNN/DaliyMail dataset show that our model achieves state-of-the-art results.
