Encoding Prior Knowledge with Eigenword Embeddings

Explore this paper's citation graph

Summary

A way to incorporate prior knowledge into CCA is described, a theoretical justification for it is given, and it is tested by deriving word embeddings and evaluating them on a myriad of datasets.

Type
preprint
Published
2015-09-03
Cited by
27
References
58
Access
Open access

Keywords

Word (group theory), Canonical correlation, Dimension (graph theory), Computer science, Context (archaeology)

References

Cited by

Related papers