
-
An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks
Many tasks in natural language processing involve predicting structured ...
read it
-
An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models
Recent work has shown that pre-trained language models such as BERT impr...
read it
-
ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
We propose to train a non-autoregressive machine translation model to mi...
read it
-
Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
Deep energy-based models are powerful, but pose challenges for learning ...
read it
-
Generating Diverse Story Continuations with Controllable Semantics
We propose a simple and effective modeling framework for controlled gene...
read it
-
Benchmarking Approximate Inference Methods for Neural Structured Prediction
Exact structured inference with neural network scoring functions is comp...
read it
-
Learning Approximate Inference Networks for Structured Prediction
Structured prediction energy networks (SPENs; Belanger & McCallum 2016) ...
read it
-
Learning to Embed Words in Context for Syntactic Tasks
We present models for embedding words in the context of surrounding word...
read it
-
Network Inference by Learned Node-Specific Degree Prior
We propose a novel method for network inference from partially observed ...
read it