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

TL;DR

This paper introduces T-STAR, a novel style transfer model that uses Abstract Meaning Representation (AMR) as an intermediate, improving content preservation and reducing hallucinations compared to existing methods.

Contribution

T-STAR is the first model to utilize AMR as an intermediate representation for text style transfer, enhancing content preservation and reducing hallucinations.

Findings

Achieves 15.2% higher content preservation than state-of-the-art methods.

Maintains style accuracy with only about 3% loss.

Reduces hallucinations by up to 50% in human evaluations.

Abstract

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% higher content preservation with negligible loss (3% approx.) in style accuracy. Through detailed human evaluation with 90,000 ratings, we also show that T-STAR has up to 50% lesser hallucinations compared to state of the art TST models.