We present PARADE, an end-to-end Transformer-based model that considers document-level context for document reranking. PARADE leverages passage-level relevance representations to predict a document relevance score, overcoming the limitations of previous approaches that perform inference on passages independently. Experiments on two ad-hoc retrieval benchmarks demonstrate PARADE's effectiveness over such methods. We conduct extensive analyses on PARADE's efficiency, highlighting several strategies for improving it. When combined with knowledge distillation, a PARADE model with 72% fewer parameters achieves effectiveness competitive with previous approaches using BERT-Base. Our code is available at https: //github.com/canjiali/PARADE.

Pseudo relevance feedback (PRF) is commonly used to boost the performance of traditional information retrieval (IR) models by using top-ranked documents to identify and weight new query terms, thereby reducing the effect of query-document vocabulary mismatches. While neural retrieval models have recently demonstrated strong results for adhoc retrieval, combining them with PRF is not straightforward due to incompatibilities between existing PRF approaches and neural architectures. To bridge this gap, we propose an end-to-end neural PRF framework that can be used with existing neural IR models by embedding different neural models as building blocks. Extensive experiments on two standard test collections confirm the effectiveness of the proposed NPRF framework in improving the performance of two state-of-theart neural IR models.

Pre-trained transformer models, such as BERT and T5, have shown to be highly effective at ad-hoc passage and document ranking. Due to the inherent sequence length limits of these models, they need to process document passages one at a time rather than processing the entire document sequence at once. Although several approaches for aggregating passage-level signals into a document-level relevance score have been proposed, there has yet to be an extensive comparison of these techniques. In this work, we explore strategies for aggregating relevance signals from a document’s passages into a final ranking score. We find that passage representation aggregation techniques can significantly improve over score aggregation techniques proposed in prior work, such as taking the maximum passage score. We call this new approach PARADE. In particular, PARADE can significantly improve results on collections with broad information needs where relevance signals can be spread throughout the document (such as TREC Robust04 and GOV2). Meanwhile, less complex aggregation techniques may work better on collections with an information need that can often be pinpointed to a single passage (such as TREC DL and TREC Genomics). We also conduct efficiency analyses and highlight several strategies for improving transformer-based aggregation.

No abstract