SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2101.08751 · 2021

Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Pre-trained deep language models~(LM) have advanced the state-of-the-art of text retrieval. Rerankers fine-tuned from deep LM estimates candidate relevance based on rich contextualized matching signals. Meanwhile, deep LMs can also be leveraged to improve search index, building retrievers with better recall. One would expect a straightforward combination of both in a pipeline to have additive performance gain. In this paper, we discover otherwise and that popular reranker cannot fully exploit the improved retrieval result. We, therefore, propose a Localized Contrastive Estimation (LCE) for training rerankers and demonstrate it significantly improves deep two-stage models.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2101.08751")
get_code_for_paper("2101.08751")
have("2101.08751")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2101.08751.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2101.08751.svg)](https://syntology.ai/paper/2101.08751)

Connect an agent — have() is free.