The eigenspace overlap score, a subspace-preservation measure between compressed and uncompressed embeddings, predicts downstream performance and selects better compressed embeddings more reliably than prior quality measures.
Globally normalized transition-based neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
On the Downstream Performance of Compressed Word Embeddings
The eigenspace overlap score, a subspace-preservation measure between compressed and uncompressed embeddings, predicts downstream performance and selects better compressed embeddings more reliably than prior quality measures.