GLoMo: Unsupervised Learning of Transferable Relational Graphs
Zhilin Yang, Jake Zhao, Bhuwan Dhingra, Kaiming He, William W. Cohen, Russ R. Salakhutdinov, Yann LeCun
–Neural Information Processing Systems
This work explores the possibility oflearning generic latentrelationalgraphs thatcapturedependencies betweenpairsofdataunits(e.g., words or pixels) from large-scale unlabeled data and transferring the graphs to downstream tasks.
Neural Information Processing Systems
Feb-12-2026, 22:12:45 GMT
- Country:
- North America
- Canada > Quebec
- Montreal (0.04)
- United States
- Oregon > Multnomah County
- Portland (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- Oregon > Multnomah County
- Canada > Quebec
- North America
- Technology: