• Publications
  • Influence
Painless Unsupervised Learning with Features
TLDR
We show how features can easily be added to standard generative models for unsupervised learning, without requiring complex new training methods. Expand
  • 228
  • 53
  • PDF
Speaker-Follower Models for Vision-and-Language Navigation
TLDR
We propose an approach to vision-and-language navigation that addresses both these issues with an embedded speaker model and a panoramic action space. Expand
  • 127
  • 47
  • PDF
Learning Bilingual Lexicons from Monolingual Corpora
TLDR
We present a method for learning bilingual translation lexicons from monolingual corpora. Expand
  • 328
  • 45
  • PDF
Learning Whom to Trust with MACE
TLDR
We build a generative model of the annotation process that learns in an unsupervised fashion to identify which annotators are trustworthy and predict the correct underlying labels. Expand
  • 185
  • 40
  • PDF
Improved Variational Autoencoders for Text Modeling using Dilated Convolutions
TLDR
We show that with the right decoder, VAE can outperform LSTM language models for generative modeling of text. Expand
  • 221
  • 36
  • PDF
Jointly Learning to Extract and Compress
TLDR
We learn a joint model of sentence extraction and compression for multi-document summarization. Expand
  • 201
  • 25
  • PDF
Lagging Inference Networks and Posterior Collapse in Variational Autoencoders
TLDR
We propose an extremely simple modification to VAE training to reduce inference lag: depending on the model's current mutual information between latent variable and observation, we aggressively optimize the inference network before performing model update. Expand
  • 110
  • 25
  • PDF
Unsupervised Text Style Transfer using Language Models as Discriminators
TLDR
We use a language model as the discriminator in GAN-based unsupervised style transfer systems to ensure that transferred sentences are similar to sentences in the target domain. Expand
  • 147
  • 18
  • PDF
An Empirical Investigation of Statistical Significance in NLP
TLDR
We investigate two aspects of the empirical behavior of paired significance tests for NLP systems. Expand
  • 117
  • 15
  • PDF
Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints
TLDR
We present a discriminative model for single-document summarization that integrally combines compression and anaphoricity constraints. Expand
  • 98
  • 13
  • PDF