PARADE: Passage Representation Aggregation for Document Reranking
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>.
READ FULL TEXT