In a 210-pair bilingual lexicon induction evaluation, unsupervised cross-lingual embeddings underperform weakly supervised methods on every pair, including 87 pairs where they collapse to near-zero accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do We Really Need Fully Unsupervised Cross-Lingual Embeddings?
In a 210-pair bilingual lexicon induction evaluation, unsupervised cross-lingual embeddings underperform weakly supervised methods on every pair, including 87 pairs where they collapse to near-zero accuracy.