paper-with-me

홈 › Papers

Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach

2021-05-17 · Xu Ma, Pengjie Wang, Hui Zhao, Shaoguo Liu, Chuhan Zhao, Wei Lin, Kuang-Chih Lee, Jian Xu, Bo Zheng

In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted. Such architecture usually consists of matching, pre-ranking, ranking, and re-ranking stages. In the pre-ranking stage, vector-product based models with representation-focused architecture are commonly adopted to account for system efficiency. However, it brings a significant loss to the effectiveness of the system. In this paper, a novel pre-ranking approach is proposed which supports complicated models with interaction-focused architecture. It achieves a better tradeoff between effectiveness and efficiency by utilizing the proposed learnable Feature Selection method based on feature Complexity and variational Dropout (FSCD). Evaluations in a real-world e-commerce sponsored search system for a search engine demonstrate that utilizing the proposed pre-ranking, the effectiveness of the system is significantly improved. Moreover, compared to the systems with conventional pre-ranking models, an identical amount of computational resource is consumed.

📄 PDF Abstract BibTeX arXiv:2105.07706

Code (0)

등록된 구현이 없습니다.

Tasks

feature selectionRe-Ranking

Methods 이 논문이 사용한 방법론

Feature Selection Feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables,…
Variational Dropout Variational Dropout is a regularization technique based on dropout, but uses a variational inference grounded approach. In…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Salience Rank: Efficient Keyphrase Extraction with Topic Modeling

2017-07-01 · ACL 2017 7 · Nedelina Teneva, Weiwei Cheng

Topical PageRank (TPR) uses latent topic distribution inferred by Latent Dirichlet Allocation (LDA) to perform ranking of noun phrases extracted from documents. The ranking procedure consists of running PageRank K times,…

Keyphrase ExtractionPart-Of-Speech TaggingSpecificity

Learning to Rank in the Age of Muppets: Effectiveness–Efficiency Tradeoffs in Multi-Stage Ranking

2021-11-01 · EMNLP (sustainlp) 2021 11 · Yue Zhang, ChengCheng Hu, Yuqi Liu, Hui Fang 외

It is well known that rerankers built on pretrained transformer models such as BERT have dramatically improved retrieval effectiveness in many tasks. However, these gains have come at substantial costs in terms of effici…

Document RankingLearning-To-RankRerankingRetrieval

Efficient and Effective Tree-based and Neural Learning to Rank

2023-05-15 · Sebastian Bruch, Claudio Lucchese, Franco Maria Nardini

This monograph takes a step towards promoting the study of efficiency in the era of neural information retrieval by offering a comprehensive survey of the literature on efficiency and effectiveness in ranking, and to a l…

Information RetrievalLearning-To-RankRetrieval

Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers

2025-07-08 · Zhiyuan Peng, Ting-Ruen Wei, Tingyu Song, Yilun Zhao 외

Large Language Models (LLMs) have recently been applied to reranking tasks in information retrieval, achieving strong performance. However, their high computational demands often hinder practical deployment. Existing stu…

Information RetrievalReranking

Pretrained Transformers for Text Ranking: BERT and Beyond

2020-10-13 · NAACL 2021 4 · Jimmy Lin, Rodrigo Nogueira, Andrew Yates

The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in …

Information RetrievalRerankingRetrievalSentence+1