The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models

Abstract

We propose a design pattern for tackling text ranking problems, dubbed "Expando-Mono-Duo", that has been empirically validated for a number of ad hoc retrieval tasks in different domains. At the core, our design relies on pretrained sequence-to-sequence models within a standard multi-stage ranking architecture. "Expando" refers to the use of document expansion techniques to enrich keyword representations of texts prior to inverted indexing. "Mono" and "Duo" refer to components in a reranking pipeline based on a pointwise model and a pairwise model that rerank initial candidates retrieved using keyword search. We present experimental results from the MS MARCO passage and document ranking tasks, the TREC 2020 Deep Learning Track, and the TREC-COVID challenge that validate our design. In all these tasks, we achieve effectiveness that is at or near the state of the art, in some cases using a zero-shot approach that does not exploit any training data from the target task. To support replicability, implementations of our design pattern are open-sourced in the Pyserini IR toolkit and PyGaggle neural reranking library.

References in corpus (18)

• A Deep Relevance Matching Model for Ad-hoc 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
• Passage Re-ranking with BERT
• Reformer: The Efficient Transformer
• Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
• Document Expansion by Query Prediction
• Multi-Stage Document Ranking with BERT
• Hierarchical Neural Story Generation
• Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval
• Cascade Ranking for Operational E-commerce Search
• Pretrained Transformers for Text Ranking: BERT and Beyond
• RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
• Learning-to-Rank with BERT in TF-Ranking
• Complementing Lexical Retrieval with Semantic Residual Embedding
• Distilling Dense Representations for Ranking using Tightly-Coupled Teachers
• The Greedy Miser: Learning under Test-time Budgets

Cited by in corpus (10)

• Pretrained Transformers for Text Ranking: BERT and Beyond
• Retrieving Supporting Evidence for Generative Question Answering
• The Information Retrieval Experiment Platform
• Adaptive Re-Ranking with a Corpus Graph
• Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations
• mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset
• Building Efficient and Effective OpenQA Systems for Low-Resource Languages
• Rewriting Conversational Utterances with Instructed Large Language Models
• Multistage BiCross encoder for multilingual access to COVID-19 health information
• IntenT5: Search Result Diversification using Causal Language Models