LTRRS: A Learning to Rank Based Algorithm for Resource Selection in Distributed Information Retrieval

Wu, Tianfeng; Liu, Xiaofeng; Dong, Shen

doi:10.1007/978-3-030-31624-2_5

Cited by 4 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dai et al [7] proposed a learning to rank method where they trained an SVMrank model based on features such as query-independent information, termbased statistics and CSI-based features. Another method is LTRRS [50], which uses term matching, CSI based, and topical relevance features. These features are combined to build a LambdaMART model that directly optimizes resources ranking list based on the nDCG metric to rank resources.…”

Section: Related Workmentioning

confidence: 99%

“…A rich line of methods exists for the resource representation and selection problems. Recent years have seen a great interest of application of learning to rank algorithms to the resource selection problem [2,7,50]. However, these approaches do not consider finegrained semantic information from both queries and resources, and are mainly limited to the statistical information like term and document frequencies of the sampled documents available in a Centralized Sample Index (CSI) [36].…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we propose a learning to rank based resource selection algorithm, named FedGNN. Learning to rank has attracted lots of research interest for ranking documents [15,35,39,53], however, its application to ranking resources has not been studied in depth [7,22,50]. Resource selection is tightly coupled with the resource representation problem [46,50].…”

Section: Introductionmentioning

confidence: 99%

“…Learning to rank has attracted lots of research interest for ranking documents [15,35,39,53], however, its application to ranking resources has not been studied in depth [7,22,50]. Resource selection is tightly coupled with the resource representation problem [46,50]. Hence, in this paper, we propose a solution that addresses both of these problems.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning To Rank Resources with GNN

Ergashev

Dragut

Meng

2023

Proceedings of the ACM Web Conference 2023

View full text Add to dashboard Cite

As the content on the Internet continues to grow, many new dynamically changing and heterogeneous sources of data constantly emerge. A conventional search engine cannot crawl and index at the same pace as the expansion of the Internet. Moreover, a large portion of the data on the Internet is not accessible to traditional search engines. Distributed Information Retrieval (DIR) is a viable solution to this as it integrates multiple shards (resources) and provides a unified access to them. Resource selection is a key component of DIR systems. There is a rich body of literature on resource selection approaches for DIR. A key limitation of the existing approaches is that they primarily use term-based statistical features and do not generally model resource-query and resource-resource relationships. In this paper, we propose a graph neural network (GNN) based approach to learning-to-rank that is capable of modeling resource-query and resource-resource relationships. Specifically, we utilize a pre-trained language model (PTLM) to obtain semantic information from queries and resources. Then, we explicitly build a heterogeneous graph to preserve structural information of query-resource relationships and employ GNN to extract structural information. In addition, the heterogeneous graph is enriched with resource-resource type of edges to further enhance the ranking accuracy. Extensive experiments on benchmark datasets show that our proposed approach is highly effective in resource selection. Our method outperforms the state-of-the-art by 6.4% to 42% on various performance metrics. CCS CONCEPTS• Information systems → Learning to rank; Combination, fusion and federated search.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning To Rank Resources with GNN

Ergashev

Dragut

Meng

2023

Proceedings of the ACM Web Conference 2023

View full text Add to dashboard Cite

show abstract

“…Learning to rank (L2R) techniques have been considered an alternative to traditional document-ranking approaches in recent years. Several research works [7,[9][10][11][12][13] have used L2R for various retrieval tasks. In these techniques, a set of queries, each associated with the ranked list of documents and their relevance judgments, is exploited as training data [14].…”

Section: Introductionmentioning

confidence: 99%

Using Ant Colony Optimization for Results Merging in Federated Search

Garba

Khalid

Shah

et al. 2023

Preprint

View full text Add to dashboard Cite

Federated search routes the user's search query to multiple component collections and presents a merged results list in ranked order by comparing the relevance score of each returned result. However, the heterogeneity of the component collections makes it challenging for the central broker to compare these relevance scores while fusing the results in ranked order. To address this issue, most existing approaches merged the returned results by changing the document ranks to their ranking scores or downloading the documents and computing their relevance score at query time. However, these approaches are less efficient as the former suffer from limited efficiency of results merging due to negligible overlapping documents among the component collections, and the latter is resource intensive. This research addresses this problem by proposing a new method that extracts features of both the documents and component collections from the available information provided by the collections at querying time. Next, each document and its collection features are exploited together to establish the document relevance score. The ant colony optimization is then used for information foraging to create a merged results list. The empirical results on a real-world dataset demonstrate significant improvements by the proposed approach over baseline approaches.

show abstract

Federated search techniques: an overview of the trends and state of the art

Garba

Khalid

2023

Knowl Inf Syst

View full text Add to dashboard Cite

LTRRS: A Learning to Rank Based Algorithm for Resource Selection in Distributed Information Retrieval

Cited by 4 publications

References 13 publications

Learning To Rank Resources with GNN

Learning To Rank Resources with GNN

Using Ant Colony Optimization for Results Merging in Federated Search

Federated search techniques: an overview of the trends and state of the art

Contact Info

Product

Resources

About