Information Retrieval: Recent Advances and Beyond

Abstract

In this paper, we provide a detailed overview of the models used for information retrieval in the first and second stages of the typical processing chain. We discuss the current state-of-the-art models, including methods based on terms, semantic retrieval, and neural. Additionally, we delve into the key topics related to the learning process of these models. This way, this survey offers a comprehensive understanding of the field and is of interest for for researchers and practitioners entering/working in the information retrieval domain.

References in corpus (69)

• BioBERT: a pre-trained biomedical language representation model for biomedical text mining
• LexRank: Graph-based Lexical Centrality as Salience in Text Summarization
• Cross-lingual Language Model Pretraining
• VisualBERT: A Simple and Performant Baseline for Vision and Language
• A Deep Relevance Matching Model for Ad-hoc Retrieval
• ERNIE: Enhanced Representation through Knowledge Integration
• Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval
• CORD-19: The COVID-19 Open Research Dataset
• End-to-End Neural Ad-hoc Ranking with Kernel Pooling
• Deeper Text Understanding for IR with Contextual Neural Language Modeling
• LSTM-based Deep Learning Models for Non-factoid Answer Selection
• KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
• CEDR: Contextualized Embeddings for Document Ranking
• Efficient Natural Language Response Suggestion for Smart Reply
• Document Expansion by Query Prediction
• Multi-Stage Document Ranking with BERT
• DeepRank: A New Deep Architecture for Relevance Ranking in Information Retrieval
• Introducing LETOR 4.0 Datasets
• Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
• Understanding the Behaviors of BERT in Ranking
• Graph Enhanced Representation Learning for News Recommendation
• Simple Applications of BERT for Ad Hoc Document Retrieval
• Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN
• Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval
• Overview of the TREC 2020 deep learning track
• TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank
• Modeling Diverse Relevance Patterns in Ad-hoc Retrieval
• A Dual Embedding Space Model for Document Ranking
• Rethinking Search: Making Domain Experts out of Dilettantes
• Neural Vector Spaces for Unsupervised Information Retrieval
• WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
• Critically Examining the "Neural Hype": Weak Baselines and the Additivity of Effectiveness Gains from Neural Ranking Models
• A Study of MatchPyramid Models on Ad-hoc Retrieval
• Zero-shot Text Classification With Generative Language Models
• Few-Shot Conversational Dense Retrieval
• Expansion via Prediction of Importance with Contextualization
• End-to-End Retrieval in Continuous Space
• A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques
• Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation
• SparTerm: Learning Term-based Sparse Representation for Fast Text Retrieval
• RepBERT: Contextualized Text Embeddings for First-Stage Retrieval
• Efficient Document Re-Ranking for Transformers by Precomputing Term Representations
• Distilling Dense Representations for Ranking using Tightly-Coupled Teachers
• Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval
• ST-MoE: Designing Stable and Transferable Sparse Expert Models
• Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage Expansion
• PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval
• Distilling Knowledge from Reader to Retriever for Question Answering
• PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval
• An Updated Duet Model for Passage Re-ranking
• Is Retriever Merely an Approximator of Reader?
• Embedding-based Zero-shot Retrieval through Query Generation
• Joint Learning of Deep Retrieval Model and Product Quantization based Embedding Index
• Off the Beaten Path: Let's Replace Term-Based Retrieval with k-NN Search
• Incorporating Query Term Independence Assumption for Efficient Retrieval and Ranking using Deep Neural Networks
• RLIRank: Learning to Rank with Reinforcement Learning for Dynamic Search
• Improving Bi-encoder Document Ranking Models with Two Rankers and Multi-teacher Distillation
• Efficient Neural Ranking using Forward Indexes
• Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently
• DeepTileBars: Visualizing Term Distribution for Neural Information Retrieval
• Match-Tensor: a Deep Relevance Model for Search
• SpaDE: Improving Sparse Representations using a Dual Document Encoder for First-stage Retrieval
• Learning-to-Rank at the Speed of Sampling: Plackett-Luce Gradient Estimation With Minimal Computational Complexity
• DynamicRetriever: A Pre-training Model-based IR System with Neither Sparse nor Dense Index
• Scattered or Connected? An Optimized Parameter-efficient Tuning Approach for Information Retrieval
• LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching
• Densifying Sparse Representations for Passage Retrieval by Representational Slicing
• EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval
• A Discriminative Semantic Ranker for Question Retrieval

Cited by in corpus (4)

• A Survey on Retrieval And Structuring Augmented Generation with Large Language Models
• Bias-Aware Agent: Enhancing Fairness in AI-Driven Knowledge Retrieval
• From Bugs to Benefits: Improving User Stories by Leveraging Crowd Knowledge with CrUISE-AC
• ReCap: Event-Aware Image Captioning with Article Retrieval and Semantic Gaussian Normalization