English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Dense retrievers encode queries and documents and map them in an embeddingspace using pre-trained language models. These embeddings need to behigh-dimensional to fit training signals and guarantee the retrievaleffectiveness of dense retrievers. However, these high-dimensional embeddingslead to larger index storage and higher retrieval latency. To reduce theembedding dimensions of dense retrieval, this paper proposes a ConditionalAutoencoder (ConAE) to compress the high-dimensional embeddings to maintain thesame embedding distribution and better recover the ranking features. Ourexperiments show that ConAE is effective in compressing embeddings by achievingcomparable ranking performance with its teacher model and making the retrievalsystem more efficient. Our further analyses show that ConAE can alleviate theredundancy of the embeddings of dense retrieval with only one linear layer. Allcodes of this work are available at https://github.com/NEUIR/ConAE.

Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder