T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation

12/03/2022
by   Anubhav Jangra, et al.
0

Unavailability of parallel corpora for training text style transfer (TST) models is a very challenging yet common scenario. Also, TST models implicitly need to preserve the content while transforming a source sentence into the target style. To tackle these problems, an intermediate representation is often constructed that is devoid of style while still preserving the meaning of the source sentence. In this work, we study the usefulness of Abstract Meaning Representation (AMR) graph as the intermediate style agnostic representation. We posit that semantic notations like AMR are a natural choice for an intermediate representation. Hence, we propose T-STAR: a model comprising of two components, text-to-AMR encoder and a AMR-to-text decoder. We propose several modeling improvements to enhance the style agnosticity of the generated AMR. To the best of our knowledge, T-STAR is the first work that uses AMR as an intermediate representation for TST. With thorough experimental evaluation we show T-STAR significantly outperforms state of the art techniques by achieving on an average 15.2 approx.) in style accuracy. Through detailed human evaluation with 90,000 ratings, we also show that T-STAR has up to 50 to state of the art TST models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/26/2019

Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus

Text style transfer rephrases a text from a source style (e.g., informal...
research
08/02/2017

Enterprise to Computer: Star Trek chatbot

Human interactions and human-computer interactions are strongly influenc...
research
05/31/2019

Effective writing style imitation via combinatorial paraphrasing

Stylometry can be used to profile authors based on their written text. T...
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
05/18/2018

Style Obfuscation by Invariance

The task of obfuscating writing style using sequence models has previous...
research
10/12/2022

On Text Style Transfer via Style Masked Language Models

Text Style Transfer (TST) is performable through approaches such as late...
research
11/15/2014

Introduction to ROSS: A New Representational Scheme

ROSS ("Representation, Ontology, Structure, Star") is introduced as a ne...

Please sign up or login with your details

Forgot password? Click here to reset