Query-based open-domain NLP tasks require information synthesis from long and
diverse web results. Current approaches extractively select portions of web
text as input to Sequence-to-Sequence models using methods such as TF-IDF
ranking. We propose constructing a local graph structured knowledge base for
each query, which compresses the web search information and reduces redundancy.
We show that by linearizing the graph into a structured input sequence, models
can encode the graph representations within a standard Sequence-to-Sequence
setting. For two generative tasks with very long text input, long-form question
answering and multi-document summarization, feeding graph representations as
input can achieve better performance than using retrieved text portions.

本文提出一种构建基于本地图形结构化知识库的方法，该方法可以压缩网络搜索信息，并减少冗余，用于 open-domain NLP 任务中，通过将图形线性化为结构化输入序列，可以实现比使用检索的文本部分更好的性能，适用于长文本输入的生成任务，例如长篇问题回答和多文档总结。