Unsupervised Content Discovery from Concise Summaries

摘要

Domain adaptation is a time consuming and costly procedure calling for the development of algorithms and tools to facilitate its automation. This paper presents an unsupervised algorithm able to learn the main concepts in event summaries. The method takes as input a set of domain summaries annotated with shallow linguistic information and produces a domain template. We demonstrate the viability of the method by applying it to three different domains and two languages. We have evaluated the generated templates against human templates obtaining encouraging results.