Reference-guided Style-Consistent Content Transfer

verfasst von

Wei Fan Chen, Milad Alshomary, Maja Stahl, Khalid Al Khatib, Benno Stein, Henning Wachsmuth

Abstract

In this paper, we introduce the task of style-consistent content transfer, which concerns modifying a text's content based on a provided reference statement while preserving its original style. We approach the task by employing multi-task learning to ensure that the modified text meets three important conditions: reference faithfulness, style adherence, and coherence. In particular, we train three independent classifiers for each condition. During inference, these classifiers are used to determine the best modified text variant. Our evaluation, conducted on hotel reviews and news articles, compares our approach with sequence-to-sequence and error correction baselines. The results demonstrate that our approach reasonably generates text satisfying all three conditions. In subsequent analyses, we highlight the strengths and limitations of our approach, providing valuable insights for future research directions.

Organisationseinheit(en)

Fachgebiet Maschinelle Sprachverarbeitung
Institut für Künstliche Intelligenz

Externe Organisation(en)

Rheinische Friedrich-Wilhelms-Universität Bonn
Reichsuniversität Groningen
Bauhaus-Universität Weimar

Typ

Aufsatz in Konferenzband

Seiten

13754-13768

Anzahl der Seiten

15

Publikationsdatum

2024

Publikationsstatus

Veröffentlicht

Peer-reviewed

Ja

ASJC Scopus Sachgebiete

Theoretische Informatik, Theoretische Informatik und Mathematik, Angewandte Informatik