Searching and Analyzing Big Data: Context-sensitive and Task-aware Approaches

使用Google很容易。使用Google搜索是另一回事。几十年来，信息检索取得了重大进展。然而，IR远未解决问题，仍存在许多挑战。首先，大多数Web搜索引擎将短文本查询作为输入，并输出文档的排名列表。检索决策主要基于当前查询和文档集合。给定查询的结果通常是相同的，与用户或用户发出请求的上下文无关。第二，信息检索是一个互动的过程。在当前以文档为中心的检索范式中，交互式检索被视为一系列独立的简单检索决策步骤。然而，它已经引起注意的任务感知用户会话，其中包含一系列的请求提交的用户，以满足信息需求的分析，提供了有用的洞察用户的查询行为。第三，目前大多数IR系统都使用关键字来查询和索引文档。然而，这种传统的基于关键词的信息检索模型提供的语义上下文很少，用户的信息需求的理解，这可能会导致查询和搜索中的文档不匹配。理想情况下，人们希望看到查询和文档彼此匹配，如果它们是主题相关的。因此，需要根据用户的信息需求和用户对文档的理解将语义上下文集成到IR系统中，以提高IR性能。第四，组织现在越来越多地处理PB级的数据收集。在处理大数据时，上下文敏感和任务感知方法变得更具挑战性。因此，提出新的算法和模型，可以有效地处理大数据，并在大数据场景中实现上下文敏感和任务感知的方法是非常重要的。

Using Google is easy. Finding information using Google is another matter. Over the decades, significant progress has been made in Information Retrieval (IR). However, IR is far from a solved problem and many challenges remain. First, most Web search engines take a short text query as input and output a ranked list of documents. The retrieval decision is made primarily based on the current query and document collection. The results for a given query are usually identical, independent of the user or the context in which the user made the request. Second, IR is an interactive process. With the current document-centered retrieval paradigm, interactive retrieval is treated as a sequence of independent simple retrieval decision making steps. However, it has been brought into attention that analysis of task-aware user sessions, which contain a sequence of requests submitted by a user to fulfill an information need, provides useful insight into the query behavior of the user. Third, most of present IR systems use keywords to query and index documents. However, this traditional keyword-based IR model provides little semantic context for the understanding of user information needs, which can lead to mismatch between query and document in search. Ideally, one would like to see the query and document match with each other, if they are topically relevant. Thus, the integration of semantic context according to the user's information need and the user's understanding of the documents into IR systems is needed to improve the IR performance. Fourth, organizations are now increasingly dealing with petabyte-scale collections of data. Context-sensitive and task-aware approaches become more challenging when dealing with big data. Hence, it is important to propose new algorithms and models that can effectively and efficiently process big data and implement the context-sensitive and task-aware approaches in big-data scenarios.