Gaussian Mixture Latent Vector Grammars

05/12/2018
by   Yanpeng Zhao, et al.
0

We introduce Latent Vector Grammars (LVeGs), a new framework that extends latent variable grammars such that each nonterminal symbol is associated with a continuous vector space representing the set of (infinitely many) subtypes of the nonterminal. We show that previous models such as latent variable grammars and compositional vector grammars can be interpreted as special cases of LVeGs. We then present Gaussian Mixture LVeGs (GM-LVeGs), a new special case of LVeGs that uses Gaussian mixtures to formulate the weights of production rules over subtypes of nonterminals. A major advantage of using Gaussian mixtures is that the partition function and the expectations of subtype rules can be computed using an extension of the inside-outside algorithm, which enables efficient inference and learning. We apply GM-LVeGs to part-of-speech tagging and constituency parsing and show that GM-LVeGs can achieve competitive accuracies. Our code is available at https://github.com/zhaoyanpeng/lveg.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/06/2023

Learning Mixtures of Gaussians with Censored Data

We study the problem of learning mixtures of Gaussians with censored dat...
research
12/16/2020

Optimal transport for vector Gaussian mixture models

Vector Gaussian mixture models form an important special subset of vecto...
research
06/12/2018

Gaussian mixture models with Wasserstein distance

Generative models with both discrete and continuous latent variables are...
research
03/06/2023

Guiding Energy-based Models via Contrastive Latent Variables

An energy-based model (EBM) is a popular generative framework that offer...
research
10/21/2011

Kernel Topic Models

Latent Dirichlet Allocation models discrete data as a mixture of discret...
research
06/25/2021

NP-DRAW: A Non-Parametric Structured Latent Variable Modelfor Image Generation

In this paper, we present a non-parametric structured latent variable mo...
research
02/18/2022

Gaussian Mixture Convolution Networks

This paper proposes a novel method for deep learning based on the analyt...

Please sign up or login with your details

Forgot password? Click here to reset