There has been much recent, exciting work on combining the complementary strengths of
latent variable models and deep learning. Latent variable modeling makes it easy to …

Sequence-to-sequence learning with neural networks has become the de facto standard for
sequence modeling. This approach typically models the local distribution over the next …

We present the Visually Grounded Neural Syntax Learner (VG-NSL), an approach for
learning syntactic representations and structures without any explicit supervision. The model …

There are two major classes of natural language grammar--the dependency grammar that
models one-to-one correspondences between words and the constituency grammar that …

Semantic role labeling (SRL) is a fundamental yet challenging task in the NLP community.
Recent works of SRL mainly fall into two lines: 1) BIO-based; 2) span-based. Despite …

We introduce a new task, unsupervised vision-language (VL) grammar induction. Given an
image-caption pair, the goal is to extract a shared hierarchical structure for both image and …

Unsupervised learning of syntactic structure is typically performed using generative models
with discrete latent variables and multinomial parameters. In most cases, these models have …

We describe a neural transducer that maintains the flexibility of standard sequence-to-
sequence (seq2seq) models while incorporating hierarchical phrases as a source of …

Neural lexicalized PCFGs (L-PCFGs) have been shown effective in grammar induction.
However, to reduce computational complexity, they make a strong independence …

The hidden Markov model (HMM) is a fundamental tool for sequence modeling that cleanly
separates the hidden state from the emission structure. However, this separation makes it …