Details
Original language | English |
---|---|
Title of host publication | Proceedings of the 18th ACM International Conference on Web Search and Data Mining |
Subtitle of host publication | WSDM 2025 |
Pages | 954-962 |
Number of pages | 9 |
ISBN (electronic) | 9798400713293 |
Publication status | Published - 10 Mar 2025 |
Event | 18th ACM International Conference on Web Search and Data Mining, WSDM 2025 - Hannover, Germany Duration: 10 Mar 2025 → 14 Mar 2025 |
Publication series
Name | Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining |
---|
Abstract
A central task in information retrieval and the NLP communities is relevance modeling, which aims to rank documents based on their expressed information needs Many knowledge-intensive retrieval tasks are powered by a first-stage retrieval stage for context selection, followed by a more involved task-specific model. However, using this filtering (cascading) approach inherently limits the recall of subsequent stages. Recently, adaptive re-ranking techniques have been proposed to overcome this issue by continually selecting documents from the whole corpus, rather than only considering an initial pool of documents. However, so far these approaches have been limited to heuristic design choices, particularly in terms of the criteria for document selection. In this work, we propose a unifying view of the nascent area of adaptive retrieval by proposing Quam, a query-affinity model of adaptive re-ranking that includes two complementary components: (1) a more principled algorithm for document selection, and (2) a data-driven approach to model document co-relevance during indexing. Our extensive experimental evidence shows that our proposed approach improves the recall performance by up to 26% over the standard re-ranking baselines. Further, the query affinity modelling and relevance-aware document graph components can be injected into any adaptive retrieval approach. The experimental results show the existing adaptive retrieval approach improves recall by up to 12%.
Keywords
- adaptive retrieval, clustering hypothesis, neural re-ranking
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
- Computer Science(all)
- Computer Science Applications
- Computer Science(all)
- Software
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of the 18th ACM International Conference on Web Search and Data Mining: WSDM 2025. 2025. p. 954-962 (Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Quam
T2 - 18th ACM International Conference on Web Search and Data Mining, WSDM 2025
AU - Rathee, Mandeep
AU - MacAvaney, Sean
AU - Anand, Avishek
N1 - Publisher Copyright: © 2025 Copyright held by the owner/author(s).
PY - 2025/3/10
Y1 - 2025/3/10
N2 - A central task in information retrieval and the NLP communities is relevance modeling, which aims to rank documents based on their expressed information needs Many knowledge-intensive retrieval tasks are powered by a first-stage retrieval stage for context selection, followed by a more involved task-specific model. However, using this filtering (cascading) approach inherently limits the recall of subsequent stages. Recently, adaptive re-ranking techniques have been proposed to overcome this issue by continually selecting documents from the whole corpus, rather than only considering an initial pool of documents. However, so far these approaches have been limited to heuristic design choices, particularly in terms of the criteria for document selection. In this work, we propose a unifying view of the nascent area of adaptive retrieval by proposing Quam, a query-affinity model of adaptive re-ranking that includes two complementary components: (1) a more principled algorithm for document selection, and (2) a data-driven approach to model document co-relevance during indexing. Our extensive experimental evidence shows that our proposed approach improves the recall performance by up to 26% over the standard re-ranking baselines. Further, the query affinity modelling and relevance-aware document graph components can be injected into any adaptive retrieval approach. The experimental results show the existing adaptive retrieval approach improves recall by up to 12%.
AB - A central task in information retrieval and the NLP communities is relevance modeling, which aims to rank documents based on their expressed information needs Many knowledge-intensive retrieval tasks are powered by a first-stage retrieval stage for context selection, followed by a more involved task-specific model. However, using this filtering (cascading) approach inherently limits the recall of subsequent stages. Recently, adaptive re-ranking techniques have been proposed to overcome this issue by continually selecting documents from the whole corpus, rather than only considering an initial pool of documents. However, so far these approaches have been limited to heuristic design choices, particularly in terms of the criteria for document selection. In this work, we propose a unifying view of the nascent area of adaptive retrieval by proposing Quam, a query-affinity model of adaptive re-ranking that includes two complementary components: (1) a more principled algorithm for document selection, and (2) a data-driven approach to model document co-relevance during indexing. Our extensive experimental evidence shows that our proposed approach improves the recall performance by up to 26% over the standard re-ranking baselines. Further, the query affinity modelling and relevance-aware document graph components can be injected into any adaptive retrieval approach. The experimental results show the existing adaptive retrieval approach improves recall by up to 12%.
KW - adaptive retrieval
KW - clustering hypothesis
KW - neural re-ranking
UR - http://www.scopus.com/inward/record.url?scp=105001669849&partnerID=8YFLogxK
U2 - 10.1145/3701551.3703584
DO - 10.1145/3701551.3703584
M3 - Conference contribution
AN - SCOPUS:105001669849
T3 - Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining
SP - 954
EP - 962
BT - Proceedings of the 18th ACM International Conference on Web Search and Data Mining
Y2 - 10 March 2025 through 14 March 2025
ER -