GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations

Explore this paper's citation graph

Summary

This work explores the possibility of learning generic latent relational graphs that capture dependencies between pairs of data units from large-scale unlabeled data and transferring the graphs to downstream tasks, and shows that the learned graphs are generic enough to be transferred to different embeddings on which the graphs have been trained.

Type
preprint
Published
2018-06-14
Cited by
36
References
52
Access
Open access

Keywords

Computer science, Mathematics

References

Cited by

Related papers