III: Small: Transforming Long Queries

该奖项是根据2009年《美国复苏和再投资法案》(Public Law 111-5)资助的。许多信息需求可以通过更长、更长的句子长度的查询来更容易地表达出来，但当前搜索引擎的不足迫使人们试图想出正确的关键字组合来查找相关文档。这可能非常困难，并且经常导致搜索失败。另一方面，目前的搜索引擎处理长查询的能力很差。该项目的重点是开发检索算法和查询处理技术，以显著提高长查询的有效性。一个特别的重点是将长查询转换为语义等价的查询以产生更好的搜索结果的技术。与纯语言学的释义方法不同，查询转换是在检索模型的上下文中进行的，并由检索模型指导。查询转换步骤，如词干、分割和扩展，已经研究了很多年，我们正在一个公共框架中扩展和集成这项工作。针对长查询的新查询处理技术正在使用美国国家科学基金会资助的加州大学马萨诸塞州分校Lemur工具包开发和分发，并正在使用来自Web、论坛等社交媒体网站和TREC等来源的各种文档和查询集进行评估，研究生和本科生参与其中。将利用项目网站(http://ciir.cs.umass.edu/research/longqueries)进一步传播成果。鉴于搜索是网络上最常见的两种活动之一，而且语音界面和协作问答等新的搜索方式正在增加长查询的重要性，这项研究可能会在家庭和办公室产生非常广泛的影响。

This award is funded under the American Recovery and Reinvestment Act of 2009 (Public Law 111-5).Many information needs can be more easily expressed using longer, sentence-length queries, but the inadequacies of current search engines force people to try to think up the right combination of keywords to find relevant documents. This can be very difficult and often leads to search failures. On the other hand, long queries are handled poorly by current search engines. The focus of this project is on developing retrieval algorithms and query processing techniques that will significantly improve the effectiveness of long queries. A specific emphasis is on techniques for transforming long queries into semantically equivalent queries that produce better search results. In contrast to purely linguistic approaches to paraphrasing, query transformation is done in the context of, and guided by, retrieval models. Query transformation steps such as stemming, segmentation, and expansion have been studied for many years, and we are both extending and integrating this work in a common framework. The new query processing techniques for long queries are being developed and distributed using the NSF-funded Lemur toolkit from UMass/CMU, and are being evaluated using a variety of document and query collections from sources such as the web, social media sites such as forums, and TREC, with an involvement of graduate and undergraduate students. The project Web site (http://ciir.cs.umass.edu/research/longqueries) will be used to further disseminate results. Given that search is one of the two most common activities on the web and that new modalities for search, such as voice interfaces and collaborative question answering, are increasing the importance of long queries, this research could have a very broad impact, both in the home and the office.