activity
20152020
most citedQUOTUS: The Structure of Political Media Coverage as Revealed by Quoting Patterns

15 citations · 22 across the 3 of their papers we have counts for

collaborators

14 papers

cs.CL2020

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

Tsvetomila Mihaylova, Vlad Niculae, André F. T. Martins

Latent structure models are a powerful tool for modeling language data: they can mitigate the error propagation and annotation bottleneck in pipeline systems, while simultaneously…

cs.LG2020

Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity

Gonçalo M. Correia, Vlad Niculae, Wilker Aziz +1

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or comb…

cs.LG2020

Sparse and Continuous Attention Mechanisms

André F. T. Martins, António Farinhas, Marcos Treviso +3

Exponential families are widely used in machine learning; they include many distributions in continuous and discrete domains (e.g., Gaussian, Dirichlet, Poisson, and categorical di…

cs.LG2020

LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction

Vlad Niculae, André F. T. Martins

Structured prediction requires manipulating a large number of combinatorial structures, e.g., dependency trees or alignments, either as latent or output variables. Recently, the Sp…

cs.CL2019

Adaptively Sparse Transformers

Gonçalo M. Correia, Vlad Niculae, André F. T. Martins

Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed a…

cs.CL20197 cited

Sparse Sequence-to-Sequence Models

Ben Peters, Vlad Niculae, André F. T. Martins

Sequence-to-sequence models are a powerful workhorse of NLP. Most variants employ a softmax transformation in both their attention mechanism and output layer, leading to dense alig…