# CEDR: Contextualized Embeddings for Document Ranking

## TL;DR

This paper introduces CEDR, a novel document ranking method that leverages BERT's contextualized embeddings to improve ranking accuracy, addressing practical challenges like input length and runtime performance.

## Contribution

The paper proposes CEDR, a joint approach integrating BERT's classification vector into neural ranking models, achieving superior performance over existing baselines.

## Key findings

- CEDR outperforms state-of-the-art ad-hoc ranking baselines.
- Utilizing BERT's contextualized embeddings enhances neural ranking models.
- Practical challenges like input length and runtime are addressed effectively.

## Abstract

Although considerable attention has been given to neural ranking architectures recently, far less attention has been paid to the term representations that are used as input to these models. In this work, we investigate how two pretrained contextualized language models (ELMo and BERT) can be utilized for ad-hoc document ranking. Through experiments on TREC benchmarks, we find that several existing neural ranking architectures can benefit from the additional context provided by contextualized language models. Furthermore, we propose a joint approach that incorporates BERT's classification vector into existing neural models and show that it outperforms state-of-the-art ad-hoc ranking baselines. We call this joint approach CEDR (Contextualized Embeddings for Document Ranking). We also address practical challenges in using these models for ranking, including the maximum input length imposed by BERT and runtime performance impacts of contextualized language models.