2D Matryoshka-trained embeddings beat standard Matryoshka and full-model baselines at small sizes, but lose to models trained separately for each specific layer and dimension, in both STS and retrieval.
17 mantic textual similarity, monolingual and cross-lingual evalua- tion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
2D Matryoshka Training for Information Retrieval
2D Matryoshka-trained embeddings beat standard Matryoshka and full-model baselines at small sizes, but lose to models trained separately for each specific layer and dimension, in both STS and retrieval.