J. Shane Culpepper

Tingting Wang, Shixun Huang, Zhifeng Bao et al.

Data discovery - retrieving relevant tables from a data lake in response to user queries - is a fundamental building block for downstream analytics. In practice, data discovery must support different query modalities, including natural language (NL) statements and tables, and accommodate diverse user intents, ranging from open-ended enrichment to task-driven inference for applications such as table question answering and fact verification. However, most existing methods are designed for a single query modality or a specific user intent, limiting their generalizability. We propose UniDisc, a unified data discovery framework that supports both NL statements and tables as queries and generalizes across diverse user intents without intent-specific representations or relevance modeling. UniDisc learns a common cross-modal representation model that produces unified representations for queries of different modalities and candidate tables, enabling uniform relevance assessment across discovery scenarios. Since learning such a model typically requires large labeled collections of query-table pairs, which are expensive to obtain, UniDisc instead exploits contextual signals naturally available in data lakes. Specifically, it models NL statements and tables as nodes in a heterogeneous graph with multiple edge types, and applies dual-view neighbor aggregation and joint optimization to learn robust, context-aware representations under limited supervision. These representations support flexible relevance estimation during retrieval. Experiments on seven datasets show that UniDisc consistently outperforms strong baselines on both NL- and table-based discovery.

Feng Luo, Hai Lan, Hui Luo et al.

In this paper, we study the problem of numerical multi-table question answering (MTQA) over large-scale table collections (e.g., online data repositories). This task is essential in many analytical applications. Existing MTQA solutions, such as text-to-SQL or open-domain MTQA methods, are designed for databases and struggle when applied to large-scale table collections. The key limitations include: (1) Limited support for complex table relationships; (2) Ineffective retrieval of relevant tables at scale; (3) Inaccurate answer generation. To overcome these limitations, we propose DMRAL, a Decomposition-driven Multi-table Retrieval and Answering framework for MTQA over large-scale table collections, which consists of: (1) constructing a table relationship graph to capture complex relationships among tables; (2) Table-Aligned Question Decomposer and Coverage-Aware Retriever, which jointly enable the effective identification of relevant tables from large-scale corpora by enhancing the question decomposition quality and maximizing the question coverage of retrieved tables; and (3) Sub-question Guided Reasoner, which produces correct answers by progressively generating and refining the reasoning program based on sub-questions. Experiments on two MTQA datasets demonstrate that DMRAL significantly outperforms existing state-of-the-art MTQA methods, with an average improvement of 24% in table retrieval and 55% in answer accuracy.

Hui Luo, Jingbo Zhou, Zhifeng Bao et al.

Existing spatial object recommendation algorithms generally treat objects identically when ranking them. However, spatial objects often cover different levels of spatial granularity and thereby are heterogeneous. For example, one user may prefer to be recommended a region (say Manhattan), while another user might prefer a venue (say a restaurant). Even for the same user, preferences can change at different stages of data exploration. In this paper, we study how to support top-k spatial object recommendations at varying levels of spatial granularity, enabling spatial objects at varying granularity, such as a city, suburb, or building, as a Point of Interest (POI). To solve this problem, we propose the use of a POI tree, which captures spatial containment relationships between POIs. We design a novel multi-task learning model called MPR (short for Multi-level POI Recommendation), where each task aims to return the top-k POIs at a certain spatial granularity level. Each task consists of two subtasks: (i) attribute-based representation learning; (ii) interaction-based representation learning. The first subtask learns the feature representations for both users and POIs, capturing attributes directly from their profiles. The second subtask incorporates user-POI interactions into the model. Additionally, MPR can provide insights into why certain recommendations are being made to a user based on three types of hints: user-aspect, POI-aspect, and interaction-aspect. We empirically validate our approach using two real-life datasets, and show promising performance improvements over several state-of-the-art methods.

Rodger Benham, Alistair Moffat, J. Shane Culpepper

Search engine users rarely express an information need using the same query, and small differences in queries can lead to very different result sets. These user query variations have been exploited in past TREC CORE tracks to contribute diverse, highly-effective runs in offline evaluation campaigns with the goal of producing reusable test collections. In this paper, we document the query fusion runs submitted to the first and second round of TREC COVID, using ten queries per topic created by the first author. In our analysis, we focus primarily on the effects of having our second priority run omitted from the judgment pool. This run is of particular interest, as it surfaced a number of relevant documents that were not judged until later rounds of the task. If the additional judgments were included in the first round, the performance of this run increased by 35 rank positions when using RBP p=0.5, highlighting the importance of judgment depth and coverage in assessment tasks.

Shixun Huang, Zhifeng Bao, Guoliang Li et al.

Network embedding is an effective method to learn low-dimensional representations of nodes, which can be applied to various real-life applications such as visualization, node classification, and link prediction. Although significant progress has been made on this problem in recent years, several important challenges remain, such as how to properly capture temporal information in evolving networks. In practice, most networks are continually evolving. Some networks only add new edges or nodes such as authorship networks, while others support removal of nodes or edges such as internet data routing. If patterns exist in the changes of the network structure, we can better understand the relationships between nodes and the evolution of the network, which can be further leveraged to learn node representations with more meaningful information. In this paper, we propose the Embedding via Historical Neighborhoods Aggregation (EHNA) algorithm. More specifically, we first propose a temporal random walk that can identify relevant nodes in historical neighborhoods which have impact on edge formations. Then we apply a deep learning model which uses a custom attention mechanism to induce node embeddings that directly capture temporal information in the underlying feature representation. We perform extensive experiments on a range of real-world datasets, and the results demonstrate the effectiveness of our new approach in the network reconstruction task and the link prediction task.

Harrie Oosterhuis, J. Shane Culpepper, Maarten de Rijke

Inverted indexes are vital in providing fast key-word-based search. For every term in the document collection, a list of identifiers of documents in which the term appears is stored, along with auxiliary information such as term frequency, and position offsets. While very effective, inverted indexes have large memory requirements for web-sized collections. Recently, the concept of learned index structures was introduced, where machine learned models replace common index structures such as B-tree-indexes, hash-indexes, and bloom-filters. These learned index structures require less memory, and can be computationally much faster than their traditional counterparts. In this paper, we consider whether such models may be applied to conjunctive Boolean querying. First, we investigate how a learned model can replace document postings of an inverted index, and then evaluate the compromises such an approach might have. Second, we evaluate the potential gains that can be achieved in terms of memory requirements. Our work shows that learned models have great potential in inverted indexing, and this direction seems to be a promising area for future research.

Rodger Benham, Joel Mackenzie, Alistair Moffat et al.

Rank fusion is a powerful technique that allows multiple sources of information to be combined into a single result set. However, to date fusion has not been regarded as being cost-effective in cases where strict per-query efficiency guarantees are required, such as in web search. In this work we propose a novel solution to rank fusion by splitting the computation into two parts -- one phase that is carried out offline to generate pre-computed centroid answers for queries with broadly similar information needs, and then a second online phase that uses the corresponding topic centroid to compute a result page for each query. We explore efficiency improvements to classic fusion algorithms whose costs can be amortized as a pre-processing step, and can then be combined with re-ranking approaches to dramatically improve effectiveness in multi-stage retrieval systems with little efficiency overhead at query time. Experimental results using the ClueWeb12B collection and the UQV100 query variations demonstrate that centroid-based approaches allow improved retrieval effectiveness at little or no loss in query throughput or latency, and with reasonable pre-processing requirements. We additionally show that queries that do not match any of the pre-computed clusters can be accurately identified and efficiently processed in our proposed ranking pipeline.

Joel Mackenzie, J. Shane Culpepper, Roi Blanco et al.

Scalable web search systems typically employ multi-stage retrieval architectures, where an initial stage generates a set of candidate documents that are then pruned and re-ranked. Since subsequent stages typically exploit a multitude of features of varying costs using machine-learned models, reducing the number of documents that are considered at each stage improves latency. In this work, we propose and validate a unified framework that can be used to predict a wide range of performance-sensitive parameters which minimize effectiveness loss, while simultaneously minimizing query latency, across all stages of a multi-stage search architecture. Furthermore, our framework can be easily applied in large-scale IR systems, can be trained without explicitly requiring relevance judgments, and can target a variety of different efficiency-effectiveness trade-offs, making it well suited to a wide range of search scenarios. Our results show that we can reliably predict a number of different parameters on a per-query basis, while simultaneously detecting and minimizing the likelihood of tail-latency queries that exceed a pre-specified performance budget. As a proof of concept, we use the prediction framework to help alleviate the problem of tail-latency queries in early stage retrieval. On the standard ClueWeb09B collection and 31k queries, we show that our new hybrid system can reliably achieve a maximum query time of 200 ms with a 99.99% response time guarantee without a significant loss in overall effectiveness. The solutions presented are practical, and can easily be used in large-scale distributed search engine deployments with a small amount of additional overhead.

J. Shane Culpepper, Charles L. A. Clarke, Jimmy Lin

Modern multi-stage retrieval systems are comprised of a candidate generation stage followed by one or more reranking stages. In such an architecture, the quality of the final ranked list may not be sensitive to the quality of initial candidate pool, especially in terms of early precision. This provides several opportunities to increase retrieval efficiency without significantly sacrificing effectiveness. In this paper, we explore a new approach to dynamically predicting two different parameters in the candidate generation stage which can directly affect the overall efficiency and effectiveness of the entire system. Previous work exploring this tradeoff has focused on global parameter settings that apply to all queries, even though optimal settings vary across queries. In contrast, we propose a technique which makes a parameter prediction that maximizes efficiency within a effectiveness envelope on a per query basis, using only static pre-retrieval features. The query-specific tradeoff point between effectiveness and efficiency is decided using a classifier cascade that weighs possible efficiency gains against effectiveness losses over a range of possible parameter cutoffs to make the prediction. The interesting twist in our new approach is to train classifiers without requiring explicit relevance judgments. We show that our framework is generalizable by applying it to two different retrieval parameters - selecting k in common top-k query retrieval algorithms, and setting a quality threshold, $ρ$, for score-at-a-time approximate query evaluation algorithms. Experimental results show that substantial efficiency gains are achievable depending on the dynamic parameter choice. In addition, our framework provides a versatile tool that can be used to estimate the effectiveness-efficiency tradeoffs that are possible before selecting and tuning algorithms to make machine learned predictions.

Charles L. A. Clarke, J. Shane Culpepper, Alistair Moffat

Large-scale retrieval systems are often implemented as a cascading sequence of phases -- a first filtering step, in which a large set of candidate documents are extracted using a simple technique such as Boolean matching and/or static document scores; and then one or more ranking steps, in which the pool of documents retrieved by the filter is scored more precisely using dozens or perhaps hundreds of different features. The documents returned to the user are then taken from the head of the final ranked list. Here we examine methods for measuring the quality of filtering and preliminary ranking stages, and show how to use these measurements to tune the overall performance of the system. Standard top-weighted metrics used for overall system evaluation are not appropriate for assessing filtering stages, since the output is a set of documents, rather than an ordered sequence of documents. Instead, we use an approach in which a quality score is computed based on the discrepancy between filtered and full evaluation. Unlike previous approaches, our methods do not require relevance judgments, and thus can be used with virtually any query set. We show that this quality score directly correlates with actual differences in measured effectiveness when relevance judgments are available. Since the quality score does not require relevance judgments, it can be used to identify queries that perform particularly poorly for a given filter. Using these methods, we explore a wide range of filtering options using thousands of queries, categorize the relative merits of the different approaches, and identify useful parameter combinations.