# Composite Re-Ranking for Efficient Document Search with BERT

arXiv: https://arxiv.org/abs/2103.06499 · HTML: https://mlsanity.com/paper/2103.06499/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2021.

## Built on by (most cited first, 5 of 5)

- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations](https://mlsanity.com/paper/2402.09617/) (2024)
- [MEMORY-VQ: Compression for Tractable Internet-Scale Memory](https://mlsanity.com/paper/2308.14903/) (2023)
- [Enhance Large Language Models as Recommendation Systems with Collaborative Filtering](https://mlsanity.com/paper/2510.15647/) (2025)

## Abstract (arXiv)

Although considerable efforts have been devoted to transformer-based ranking models for document search, the relevance-efficiency tradeoff remains a critical problem for ad-hoc ranking. To overcome this challenge, this paper presents BECR (BERT-based Composite Re-Ranking), a composite re-ranking scheme that combines deep contextual token interactions and traditional lexical term-matching features. In particular, BECR exploits a token encoding mechanism to decompose the query representations into pre-computable uni-grams and skip-n-grams. By applying token encoding on top of a dual-encoder architecture, BECR separates the attentions between a query and a document while capturing the contextual semantics of a query. In contrast to previous approaches, this framework does not perform expensive BERT computations during online inference. Thus, it is significantly faster, yet still able to achieve high competitiveness in ad-hoc ranking relevance. Finally, an in-depth comparison between BECR and other start-of-the-art neural ranking baselines is described using the TREC datasets, thereby further demonstrating the enhanced relevance and efficiency of BECR.