Learning to rank for information retrieval

By Tie-Yan Liu. 2009

972 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, neutral): “nd d jare never both relevant or not relevant. Since this loss function considers pairs of candidate texts, it can be characterized as belonging to the family of pairwise learning to rank approaches [Liu, 2009, Li, 2011]. For additional training details, including hyperparameter settings, we refer t”
Learning to Branch in Mixed Integer Programming (2016, positive): “In a second phase, we learn an easy-to-evaluate surrogate function that mimics SB, by solving a learning-to-rank problem common in ML (Liu 2009), with the collected data being used for training.”
Document Ranking with a Pretrained Sequence-to-Sequence Model (2020, neutral): “Prior to deep learning, researchers and practitioners mostly adopt the paradigm known as “learning to rank”, which is heavily driven by manual feature engineering (Liu, 2009; Li, 2011).”
Multi-Stage Document Ranking with BERT (2019, neutral): “Although machine-learned ranking models have been well studied since the mid-2000s under the banner of “learning to rank”, the paradigm is heavily driven by manual feature engineering (Liu, 2009; Li, 2011); commercial web search engines are known to incorporate thousands of features (or more) in the”
Monotonic Calibrated Interpolated Look-Up Tables (2015, neutral): “The feature values are assumed to be bounded and linearly scaled to ﬁt the lattice, so that the d th feature vector value i th training sample with D components.”
Semantic Matching in Search (2014, positive): “In fact, machine learning techniques for the purpose, referred to as learning to rank, have been intensively studied and widely applied in web search [128, 115].”
A Short Introduction to Learning to Rank (2011, neutral): “Intensive studies have been conducted on the problem and significant progress has been made [1], [2].”
Learning to Rank for Information Retrieval and Natural Language Processing (2011, neutral): “Learning to rank is a sub-area of machine learning, studying methodologies and theories for automatically constructing a model from data for a ranking problem [1, 2, 3].”
Recommender Systems (2016, neutral): “The problem of learning to rank is widely studied in the classification, internet search, and information retrieval [15, 115, 284, 370].”
Learning to Navigate for Fine-grained Classification (2018, neutral): “Learning to rank is drawing attention in the ﬁeld of machine learning and information retrieval [30].”
Cascade Ranking for Operational E-commerce Search (2017, positive): “While most research in learning to rank for search only focuses on the effectiveness issue (e.g., [6, 10, 16]), some valuable prior research of learning to efficiently rank (e.g., [21, 23]) has been proposed to address the trade-off between effectiveness and efficiency.”
Uncovering ChatGPT’s Capabilities in Recommender Systems (2023, positive): “To accomplish this, current learning-to-rank (LTR) methods empower different capabilities to recommender systems via corresponding loss functions, including point-wise ranking capability, pair-wise ranking capability and listwise ranking capability [18].”
A cascade ranking model for efficient ranked retrieval (2011, positive): “, O(St−1 + αtSt, qi) ≈ O(St−1, qi) + αtO(St, qi), where St−1 denotes the additive model up to stage t − 1, St is a stage and αt is the local weight [30, 16].”
EsdRank: Connecting Query and Documents through External Semi-Structured Data (2015, positive): “Prior research has produced many eﬀective unsupervised retrieval models (e.g., BM25, language models, DPH) [9] and supervised learning to rank (LeToR) models (e.g., RankSVM, ListMLE) [19].”
Efficient Cost-Aware Cascade Ranking in Multi-Stage Retrieval (2017, positive): “1 INTRODUCTION Learning-to-Rank (LTR) systems are now commonly deployed by major search engine companies and they have been repeatedly shown to be highly eective for a variety of search related problems [6, 15, 26, 30].”