PARADE: Passage Representation Aggregation for Document Reranking

Li, Canjia; Yates, Andrew; MacAvaney, Sean; He, Ben; Sun, Yingfei

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Paper

PARADE: Passage Representation Aggregation for Document Reranking

MPS-Authors

/persons/resource/persons206666

Yates, Andrew
Databases and Information Systems, MPI for Informatics, Max Planck Society;

External Resource

No external resources are shared

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

arXiv:2008.09093.pdf
(Preprint), 2MB

Supplementary Material (public)

There is no public supplementary material available

Citation

Li, C., Yates, A., MacAvaney, S., He, B., & Sun, Y. (2020). PARADE: Passage Representation Aggregation for Document Reranking. Retrieved from https://arxiv.org/abs/2008.09093.

Cite as: https://hdl.handle.net/21.11116/0000-0008-06CF-9

Abstract

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 \url{https://github.com/canjiali/PARADE}.