Search Results for author:
Found 5 papers, 2 papers with code
FlowPrior: Learning Expressive Priors for Latent Variable Sentence Models
Variational autoencoders (VAEs) are widely used for latent variable modeling of text.
An Empirical Study on Model-agnostic Debiasing Strategies for Robust Natural Language Inference
The prior work on natural language inference (NLI) debiasing mainly targets at one or few known biases while not necessarily making the models more robust.
Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference
We explore training objectives for discriminative fine-tuning of our generative classifiers, showing improvements over log loss fine-tuning from prior work .
Latent-Variable Generative Models for Data-Efficient Text Classification
This model consistently outperforms both the generative and discriminative classifiers in small-data settings.
Generating Diverse Story Continuations with Controllable Semantics
We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
