Document Expansion by Query Prediction

Abstract

One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content.From the perspective of a question answering system, this might comprise questions the document can potentially answer. Following this observation, we propose a simple method that predicts which queries will be issued for a given document and then expands it with those predictions with a vanilla sequence-to-sequence model, trained using datasets consisting of pairs of query and relevant documents. By combining our method with a highly-effective re-ranking component, we achieve the state of the art in two retrieval tasks. In a latency-critical regime, retrieval results alone (without re-ranking) approach the effectiveness of more computationally expensive neural re-rankers but are much faster.

References in corpus (2)

• Passage Re-ranking with BERT
• An Updated Duet Model for Passage Re-ranking

Cited by in corpus (57)

• Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
• Information Retrieval: Recent Advances and Beyond
• Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval
• Semantic Models for the First-stage Retrieval: A Comprehensive Review
• Pretrained Transformers for Text Ranking: BERT and Beyond
• Sparse, Dense, and Attentional Representations for Text Retrieval
• RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
• GERE: Generative Evidence Retrieval for Fact Verification
• Complementing Lexical Retrieval with Semantic Residual Embedding
• RepBERT: Contextualized Text Embeddings for First-Stage Retrieval
• SparTerm: Learning Term-based Sparse Representation for Fast Text Retrieval
• The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models
• Continual Learning for Generative Retrieval over Dynamic Corpora
• Adversarial Retriever-Ranker for dense text retrieval
• Keyphrase Generation for Scientific Document Retrieval
• ABNIRML: Analyzing the Behavior of Neural IR Models
• Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
• Document Ranking with a Pretrained Sequence-to-Sequence Model
• Wacky Weights in Learned Sparse Representations and the Revenge of Score-at-a-Time Query Evaluation
• Conformer-Kernel with Query Term Independence for Document Retrieval
• B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval
• Overview of the TREC 2022 deep learning track
• Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach
• SpaDE: Improving Sparse Representations using a Dual Document Encoder for First-stage Retrieval
• Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently
• Answering Complex Open-domain Questions Through Iterative Query Generation
• Let's measure run time! Extending the IR replicability infrastructure to include performance aspects
• Optimizing Dense Retrieval Model Training with Hard Negatives
• SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval
• Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking
• Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline
• Learning Passage Impacts for Inverted Indexes
• An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models
• Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation
• Simulating Users in Interactive Web Table Retrieval
• BERT-QE: Contextualized Query Expansion for Document Re-ranking
• Scientific Claim Verification with VERT5ERINI
• IntenT5: Search Result Diversification using Causal Language Models
• Neural document expansion for ad-hoc information retrieval
• Hybrid and Collaborative Passage Reranking
• Brown University at TREC Deep Learning 2019
• Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations
• SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking
• Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance
• Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation
• RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
• GLOW : Global Weighted Self-Attention Network for Web Search
• Answer Generation through Unified Memories over Multiple Passages
• Distilling Transformers for Neural Cross-Domain Search
• Modularized Transfomer-based Ranking Framework
• Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder
• Searching Personal Collections
• Text-to-Text Multi-view Learning for Passage Re-ranking
• Can questions summarize a corpus? Using question generation for characterizing COVID-19 research
• JurisTCU: A Brazilian Portuguese Information Retrieval Dataset with Query Relevance Judgments
• Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval