Where did you get that? Towards Summarization Attribution for Analysts
This addresses the need for analysts to verify information sources in automated summaries, but it appears incremental as it builds on existing methods.
The paper tackles the problem of providing attribution for summarization by linking summary sentences to source text portions, exploring a hybrid summarization approach and a custom error analysis topology.
Analysts require attribution, as nothing can be reported without knowing the source of the information. In this paper, we will focus on automatic methods for attribution, linking each sentence in the summary to a portion of the source text, which may be in one or more documents. We explore using a hybrid summarization, i.e., an automatic paraphrase of an extractive summary, to ease attribution. We also use a custom topology to identify the proportion of different categories of attribution-related errors.