论文标题
抽象性多文件新闻摘要的无监督掩蔽目标
An Unsupervised Masking Objective for Abstractive Multi-Document News Summarization
论文作者
论文摘要
我们表明，一个简单的无监督掩蔽目标可以在抽象性多文件新闻摘要上接近监督性能。我们的方法训练一种最先进的神经摘要模型，以预测相对于多文档组的词汇中心性最高的屏蔽源文档。在对多名数据集的实验中，我们的掩盖训练目标产生了一个超过无监督方法的系统，在人类评估中，超过了最佳监督方法，而无需访问任何地面真相摘要。此外，我们评估了词汇中心的不同度量如何受到过去的提取摘要工作的启发，影响最终性能。
We show that a simple unsupervised masking objective can approach near supervised performance on abstractive multi-document news summarization. Our method trains a state-of-the-art neural summarization model to predict the masked out source document with highest lexical centrality relative to the multi-document group. In experiments on the Multi-News dataset, our masked training objective yields a system that outperforms past unsupervised methods and, in human evaluation, surpasses the best supervised method without requiring access to any ground-truth summaries. Further, we evaluate how different measures of lexical centrality, inspired by past work on extractive summarization, affect final performance.
