We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| guest400123064/distill-retriever | canonical | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| load_beir_queries | Not yet run | guest400123064/distill-retriever/ispeed.py code served (permissive licence) · get_code("293b501240690f11") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2306.11550")
get_code_for_paper("2306.11550")
have("2306.11550")
Connect an agent — have() is free.