论文标题
从无查询资源中生成以查询为重点的摘要
Generating Query Focused Summaries from Query-Free Resources
论文作者
论文摘要
大规模数据集的可用性促进了神经模型的开发，这些神经模型从单个或多个文档中创建了通用摘要。在这项工作中，我们考虑以查询为重点的摘要（QFS），该任务不容易获得查询，文档和摘要形式的培训数据。我们建议将QF分解为（1）查询建模（即，在查询的一组文档中找到支持证据）和（2）条件语言建模（即摘要生成）。我们介绍了Marge，这是一个蒙版的胭脂回归框架，用于证据估算和排名，依赖于摘要和查询的统一表示形式，因此可以将通用数据中的摘要转换为用于学习查询模型的代理查询。 QFS基准和查询类型之间的实验表明，尽管从弱监督中学习了，但我们的模型仍能达到最先进的性能。
The availability of large-scale datasets has driven the development of neural models that create generic summaries from single or multiple documents. In this work we consider query focused summarization (QFS), a task for which training data in the form of queries, documents, and summaries is not readily available. We propose to decompose QFS into (1) query modeling (i.e., finding supportive evidence within a set of documents for a query) and (2) conditional language modeling (i.e., summary generation). We introduce MaRGE, a Masked ROUGE Regression framework for evidence estimation and ranking which relies on a unified representation for summaries and queries, so that summaries in generic data can be converted into proxy queries for learning a query model. Experiments across QFS benchmarks and query types show that our model achieves state-of-the-art performance despite learning from weak supervision.
