III: Small: Efficiency Optimization for Neural Document Ranking with Compact Representations

在过去的几年中，神经模型的复兴极大地推动了信息检索领域的发展，使检索引擎能够有效地匹配和排序响应于用户查询的搜索结果。例如，这项新技术使得能够响应于查询来确定最相关的文档，即使某些查询关键字可能没有出现在这些文档中。使用深度神经模型进行排序的主要缺点是检索非常耗时。因此，这样的模型不能部署在许多实际的搜索应用程序中。该项目专注于研究执行神经排名计算的有效解决方案，所开发的技术将使用公共数据集进行评估，以评估解决方案的有效性。该项目将研究与教育计划相结合，包括本科生和研究生的参与、教材开发和外联活动。该项目开展了一项双推力研究议程，以实现有效的神经排名。第一个推力研究了一种用于双重编码体系结构的快速重新排序方案，该方案利用预计算嵌入来组成具有近似值的查询表示，并结合深度上下文标记交互和传统的词汇匹配特征。该项目的第二个主题是研究文档嵌入的紧凑表示，并在相关性和空间效率之间取得平衡，这会影响在线推理延迟。该项目利用回答查询的排序推理的复合性来近似查询嵌入，并在导出紧凑表示时解耦文档嵌入的排序贡献。这项研究将促进我们对神经信息检索中相关性和效率权衡的基本理解，并显著降低在线推理的计算和空间成本，同时保留深度学习的基本好处，以便在负担得起的计算平台上进行有效排名。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

Over the last few years, the resurgence of neural models has greatly advanced the field of information retrieval enabling retrieval engines to effectively match and rank search results in response to a user query. For example, this new technology has enable to determine the most relevant documents in response to a query even when some query keywords may not appear in these documents. The main drawback of using deep neural models for ranking is that the retrieval is extremely time consuming. As a result, such models cannot be deployed in many practical search applications. This project is focused on studying efficient solutions to perform neural ranking computation and the developed techniques will be evaluated using public datasets to assess the solution’s effectiveness. The project integrates the research with an educational plan including undergraduate and graduate students' involvement, instructional material development, and outreach activities. This project carries out a two-thrust research agenda for efficient neural ranking. The first thrust investigates a fast re-ranking scheme for a dual-encoding architecture by leveraging precomputed embeddings to compose a query representation with approximation, and combining deep contextual token interactions and traditional lexical matching features. The second thrust of this project investigates a compact representation of document embeddings and strike a balance of relevance and space efficiency which affects online inference latency. The project exploits the composite nature of ranking inference for answering a query to approximate query embeddings, and decouples ranking contribution of document embeddings in deriving a compact representation. This research will advance our fundamental understanding of relevance and efficiency tradeoffs in neural information retrieval, and significantly reduce the computing and space cost of online inference while retaining the essential benefits of deep learning for effective ranking on affordable computing platforms.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.