DeepAI AI Chat
Log In Sign Up

Towards Dynamic Computation Graphs via Sparse Latent Structure

by   Vlad Niculae, et al.
Unbabel Inc.
cornell university

Deep NLP models benefit from underlying structures in the data---e.g., parse trees---typically extracted using off-the-shelf parsers. Recent attempts to jointly learn the latent structure encounter a tradeoff: either make factorization assumptions that limit expressiveness, or sacrifice end-to-end differentiability. Using the recently proposed SparseMAP inference, which retrieves a sparse distribution over latent structures, we propose a novel approach for end-to-end learning of latent structure predictors jointly with a downstream predictor. To the best of our knowledge, our method is the first to enable unrestricted dynamic computation graph construction from the global latent structure, while maintaining differentiability.


On estimation and inference in latent structure random graphs

We define a latent structure model (LSM) random graph as a random dot pr...

Learning Latent Trees with Stochastic Perturbations and Differentiable Dynamic Programming

We treat projective dependency trees as latent variables in our probabil...

Learning with Latent Structures in Natural Language Processing: A Survey

While end-to-end learning with fully differentiable models has enabled t...

Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning

Latent structure models are a powerful tool for modeling language data: ...

GraphOpt: Learning Optimization Models of Graph Formation

Formation mechanisms are fundamental to the study of complex networks, b...

Latent Domain Learning with Dynamic Residual Adapters

A practical shortcoming of deep neural networks is their specialization ...

Code Repositories


SparseMAP: differentiable sparse structure inference

view repo