Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer

05/04/2022
by   Sharan Narasimhan, et al.
5

Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. The latent space geometry of such models is organised well enough to perform on datasets where the style is "coarse-grained" i.e. a small fraction of words alone in a sentence are enough to determine the overall style label. A recent study uses a discrete token-based perturbation approach to map "similar" sentences ("similar" defined by low Levenshtein distance/ high word overlap) close by in latent space. This definition of "similarity" does not look into the underlying nuances of the constituent words while mapping latent space neighbourhoods and therefore fails to recognise sentences with different style-based semantics while mapping latent neighbourhoods. We introduce EPAAEs (Embedding Perturbed Adversarial AutoEncoders) which completes this perturbation model, by adding a finely adjustable noise component on the continuous embeddings space. We empirically show that this (a) produces a better organised latent space that clusters stylistically similar sentences together, (b) performs best on a diverse set of text style transfer tasks than similar denoising-inspired baselines, and (c) is capable of fine-grained control of Style Transfer strength. We also extend the text style transfer tasks to NLI datasets and show that these more complex definitions of style are learned best by EPAAE. To the best of our knowledge, extending style transfer to NLI tasks has not been explored before.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/29/2019

Revision in Continuous Space: Fine-Grained Control of Text Style Transfer

Typical methods for unsupervised text style transfer often rely on two k...
research
05/06/2021

Stylistic Analysis of the French Presidential Speeches: Is Macron really different?

Presidential speeches indicate the government's intentions and justifica...
research
11/01/2018

Multiple-Attribute Text Style Transfer

The dominant approach to unsupervised "style transfer" in text is based ...
research
06/12/2023

MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer

Unsupervised text style transfer task aims to rewrite a text into target...
research
02/01/2021

GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer

Non-parallel text style transfer has attracted increasing research inter...
research
01/23/2022

Gradient-guided Unsupervised Text Style Transfer via Contrastive Learning

Text style transfer is a challenging text generation problem, which aims...
research
03/27/2017

StyleBank: An Explicit Representation for Neural Image Style Transfer

We propose StyleBank, which is composed of multiple convolution filter b...

Please sign up or login with your details

Forgot password? Click here to reset