Log In Sign Up

Hierarchical Sketch Induction for Paraphrase Generation

by   Tom Hosking, et al.

We propose a generative model of paraphrase generation, that encourages syntactic diversity by conditioning on an explicit syntactic sketch. We introduce Hierarchical Refinement Quantized Variational Autoencoders (HRQ-VAE), a method for learning decompositions of dense encodings as a sequence of discrete latent variables that make iterative refinements of increasing granularity. This hierarchy of codes is learned through end-to-end training, and represents fine-to-coarse grained information about the input. We use HRQ-VAE to encode the syntactic form of an input sentence as a path through the hierarchy, allowing us to more easily predict syntactic sketches at test time. Extensive experiments, including a human evaluation, confirm that HRQ-VAE learns a hierarchical representation of the input space, and generates paraphrases of higher quality than previous systems.


page 1

page 2

page 3

page 4


Relaxed-Responsibility Hierarchical Discrete VAEs

Successfully training Variational Autoencoders (VAEs) with a hierarchy o...

Factorising Meaning and Form for Intent-Preserving Paraphrasing

We propose a method for generating paraphrases of English questions that...

Hierarchical Quantized Autoencoders

Despite progress in training neural networks for lossy image compression...

Predicting Video with VQVAE

In recent years, the task of video prediction-forecasting future video g...

NeRF-VAE: A Geometry Aware 3D Scene Generative Model

We propose NeRF-VAE, a 3D scene generative model that incorporates geome...

A Hierarchical Latent Structure for Variational Conversation Modeling

Variational autoencoders (VAE) combined with hierarchical RNNs have emer...

Preventing Posterior Collapse in Sequence VAEs with Pooling

Variational Autoencoders (VAEs) hold great potential for modelling text,...

Code Repositories


Hierarchical Sketch Induction for Paraphrase Generation (Hosking et al., ACL 2022)

view repo