Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency

June 05, 2023 Β· Declared Dead Β· πŸ› SUSTAINLP

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Yuxuan Wang, Hong Lyu arXiv ID 2306.11550 Category cs.IR: Information Retrieval Cross-listed cs.AI Citations 4 Venue SUSTAINLP Last Checked 4 months ago
Abstract
The information retrieval community has made significant progress in improving the efficiency of Dual Encoder (DE) dense passage retrieval systems, making them suitable for latency-sensitive settings. However, many proposed procedures are often too complex or resource-intensive, which makes it difficult for practitioners to adopt them or identify sources of empirical gains. Therefore, in this work, we propose a trivially simple recipe to serve as a baseline method for boosting the efficiency of DE retrievers leveraging an asymmetric architecture. Our results demonstrate that even a 2-layer, BERT-based query encoder can still retain 92.5% of the full DE performance on the BEIR benchmark via unsupervised distillation and proper student initialization. We hope that our findings will encourage the community to re-evaluate the trade-offs between method complexity and performance improvements.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Retrieval

Died the same way β€” πŸ‘» Ghosted