An official website of the United States government
Many content-based image search and instance retrieval systems implement bag-of-visual-words strategies for candidate selection. Visual processing of an image results in hundreds of visual words that make up a document, and these words are used to build an inverted index. Query processing then consists of an initial candidate selection phase that queries the inverted index, followed by more complex reranking of the candidates using various image features. The initial phase typically uses disjunctive top-k query processing algorithms originally proposed for searching text collections. Our objective in this paper is to optimize the performance of disjunctive top-k computation for candidate selection in content-based instance retrieval systems. While there has been extensive previous work on optimizing this phase for textual search engines, we are unaware of any published work that studies this problem for instance retrieval, where both index and query data are quite different from the distributions commonly found and exploited in the textual case. Using data from a commercial large-scale instance retrieval system, we address this challenge in three steps. First, we analyze the quantitative properties of index structures and queries in the system, and discuss how they differ from the case of text retrieval. Second, we describe an optimized term-at-a-time retrieval strategy that significantly outperforms baseline term-at-a-time and document-at-a-time strategies, achieving up to 66% speed-up over the most efficient baseline. Finally, we show that due to the different properties of the data, several common safe and unsafe early termination techniques from the literature fail to provide any significant performance benefits.
more »
« less
Efficient top-k document retrieval
Over the past few decades, the IR community has been making a continuous effort to improve the efficiency of search in large collections of documents. Query processing is still one of the main bottlenecks in large-scale search systems. The top-k document retrieval problem, which can be defined as reporting the k most relevant documents from a collection for a given query, can be extremely expensive, as it involves scoring large amounts of documents. In this work, we investigate the top-k document retrieval problem from several angles with the aim of improving the efficiency of this task in large-scale search systems. Finally, we briefly describe our initial findings and conclude by proposing future directions to follow.
more »
« less
- Award ID(s):
- 1718680
- PAR ID:
- 10171671
- Date Published:
- Journal Name:
- Proceedings of the 9th PhD Symposium on Future Directions in Information Access
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Dense retrieval systems conduct first-stage retrieval using embedded representations and simple similarity metrics to match a query to documents. Its effectiveness depends on encoded embeddings to capture the semantics of queries and documents, a challenging task due to the shortness and ambiguity of search queries. This paper proposes ANCE-PRF, a new query encoder that uses pseudo relevance feedback (PRF) to improve query representations for dense retrieval. ANCE-PRF uses a BERT encoder that consumes the query and the top retrieved documents from a dense retrieval model, ANCE, and it learns to produce better query embeddings directly from relevance labels. It also keeps the document index unchanged to reduce overhead. ANCE-PRF significantly outperforms ANCE and other recent dense retrieval systems on several datasets. Analysis shows that the PRF encoder effectively captures the relevant and complementary information from PRF documents, while ignoring the noise with its learned attention mechanism.more » « less
-
Query by Example is a well-known information retrieval task in which a document is chosen by the user as the search query and the goal is to retrieve relevant documents from a large collection. However, a document often covers multiple aspects of a topic. To address this scenario we introduce the task of faceted Query by Example in which users can also specify a finer grained aspect in addition to the input query document. We focus on the application of this task in scientific literature search. We envision models which are able to retrieve scientific papers analogous to a query scientific paper along specifically chosen rhetorical structure elements as one solution to this problem. In this work, the rhetorical structure elements, which we refer to as facets, indicate objectives, methods, or results of a scientific paper. We introduce and describe an expert annotated test collection to evaluate models trained to perform this task. Our test collection consists of a diverse set of 50 query documents in English, drawn from computational linguistics and machine learning venues. We carefully follow the annotation guideline used by TREC for depth-k pooling (k = 100 or 250) and the resulting data collection consists of graded relevance scores with high annotation agreement. State of the art models evaluated on our dataset show a significant gap to be closed in further work. Our dataset may be accessed here: https://github.com/iesl/CSFCube.more » « less
-
The ranked (or top-k) document retrieval problem is defined as follows: preprocess a collection{T1,T2,… ,Td}ofdstrings (called documents) of total lengthninto a data structure, such that for any given query(P,k), wherePis a string (called pattern) of lengthp ≥ 1andk ∈ [1,d]is an integer, the identifiers of thosekdocuments that are most relevant toPcan be reported, ideally in the sorted order of their relevance. The seminal work by Hon et al. [FOCS 2009 and Journal of the ACM 2014] presented anO(n)-space (in words) data structure withO(p+klogk)query time. The query time was later improved toO(p+k)[SODA 2012] and further toO(p/logσn+k)[SIAM Journal on Computing 2017] by Navarro and Nekrich, whereσis the alphabet size. We revisit this problem in the external memory model and present three data structures. The first one takesO(n)-space and answer queries inO(p/B+ logBn + k/B+log*(n/B)) I/Os, whereBis the block size. The second one takesO(nlog*(n/B)) space and answer queries in optimalO(p/B+ logBn + k/B)I/Os. In both cases, the answers are reported in the unsorted order of relevance. To handle sorted top-kdocument retrieval, we present anO(nlog(d/B))space data structure with optimal query cost.more » « less
-
The availability of massive data and computing allowing for effective data driven neural approaches is having a major impact on AI and IR research, but these models have a basic problem with efficiency. Current neural ranking models are implemented as multistage rankers: for efficiency reasons, the neural model only re-ranks the top ranked documents retrieved by a first-stage efficient ranker in response to a given query. Neural ranking models learn dense representations causing essentially every query term to match every document term, making it highly inefficient or intractable to rank the whole collection. The reliance on a first stage ranker creates a dual problem: First, the interaction and combination effects are not well understood. Second, the first stage ranker serves as a "gate-keeper" or filter effectively blocking the potential of neural models to uncover new relevant documents. In this work, we propose a standalone neural ranking model SNRM by introducing a sparsity property to learn a latent sparse representation for each query and document. This representation captures the semantic relationship between the query and documents, but is also {sparse} enough to enable constructing an inverted index for the whole collection. We parameterize the sparsity of the model to yield a retrieval model as efficient as conventional term based models. Our model gains in efficiency without loss of effectiveness: it not only outperforms the existing term matching baselines, but also performs similar to the recent re-ranking based neural models with dense representations. More generally, our results demonstrate the importance of sparsity in neural model learning and show that dense representations can be pruned effectively, giving new insights about essential semantic features and their distributions.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
