Effective summaries for search results

所有信息检索系统都返回一个搜索结果页面，其中列出了每个检索到的文档的简短摘要。这个项目将通过采用一种新的方法来理解、设计和构建这样的摘要，从而改变搜索效率。最近的工作表明，由于摘要质量差，用户无法点击高达50%的相关文件。为了加强搜索结果摘要，该项目将模拟用户在检查摘要时如何确定文件相关性；它将利用以前未开发的信息来源来显著提高摘要质量；它将创建一种新的方法，通过考虑文件的摘要性来检索相关文件。

All information retrieval systems return a search result page that lists short summaries of each retrieved document. This project will transform search effectiveness by taking a new approach to the understanding, design, and construction of such summaries. Recent work has showed that users fail to click on up to 50 per cent of relevant documents because of poor summary quality. To enhance search result summaries, this project will model how users determine document relevance when inspecting a summary; it will exploit a previously untapped source of information to dramatically improve summary quality; and, it will create a new approach to retrieving relevant documents by considering their summarisability.