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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Dual encoders perform retrieval by encoding documents and queries into dense lowdimensional vectors, scoring each document by its inner product with the query. We investigate the capacity of this architecture relative to sparse bag-of-words models and attentional neural networks. Using both theoretical and empirical analysis, we establish connections between the encoding dimension, the margin between gold and lower-ranked documents, and the document length, suggesting limitations in the capacity of fixed-length encodings to support precise retrieval of long documents. Building on these insights, we propose a simple neural model that combines the efficiency of dual encoders with some of the expressiveness of more costly attentional architectures, and explore sparse-dense hybrids to capitalize on the precision of sparse retrieval. These models outperform strong alternatives in large-scale retrieval.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2005.00181")
get_code_for_paper("2005.00181")
have("2005.00181")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2005.00181.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2005.00181)
Connect an agent — have() is free.