Efficient Compression and Querying Techniques for Massive Text Collections

网络搜索服务已经成为政府、企业和个人使用的基本工具，在我们获取知识和信息方面发挥着关键作用。在这个项目中，我们的目标是开发新的技术来表示web搜索服务的核心索引，并设计新的处理算法，以减少解决查询和提供有用和主题答案的资源需求。更高的查询吞吐量和更低的存储负载将通过降低硬件和电力成本而使提供商受益，并且将通过更好地访问信息、增强连接和协作的机会以及随着在线资源的不断增加而获得更大的长期可伸缩性而使社会受益。

Web search services have become a fundamental tool used by governments, businesses, and individuals, and play a key role in our access to knowledge and information. In this project we aim to develop new techniques for representing the indexes at the heart of web search services, and to devise new processing algorithms with reduced resource requirements for resolving queries and providing useful and topical answers. Higher query throughput and reduced storage load will benefit providers though reduced hardware and electricity costs, and will benefit society through better access to information, enhanced opportunities to connect and collaborate, and greater long-term scalability as on-line resources continue to multiply.