Reference-guided Style-Consistent Content Transfer

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autoren

Externe Organisationen

  • Rheinische Friedrich-Wilhelms-Universität Bonn
  • Reichsuniversität Groningen
  • Bauhaus-Universität Weimar
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des Sammelwerks2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings
Herausgeber/-innenNicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Seiten13754-13768
Seitenumfang15
ISBN (elektronisch)9782493814104
PublikationsstatusVeröffentlicht - 2024
VeranstaltungJoint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024 - Hybrid, Torino, Italien
Dauer: 20 Mai 202425 Mai 2024

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.

ASJC Scopus Sachgebiete

Zitieren

Reference-guided Style-Consistent Content Transfer. / Chen, Wei Fan; Alshomary, Milad; Stahl, Maja et al.
2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings. Hrsg. / Nicoletta Calzolari; Min-Yen Kan; Veronique Hoste; Alessandro Lenci; Sakriani Sakti; Nianwen Xue. 2024. S. 13754-13768.

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Chen, WF, Alshomary, M, Stahl, M, Al Khatib, K, Stein, B & Wachsmuth, H 2024, Reference-guided Style-Consistent Content Transfer. in N Calzolari, M-Y Kan, V Hoste, A Lenci, S Sakti & N Xue (Hrsg.), 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings. S. 13754-13768, Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024, Hybrid, Torino, Italien, 20 Mai 2024.
Chen, W. F., Alshomary, M., Stahl, M., Al Khatib, K., Stein, B., & Wachsmuth, H. (2024). Reference-guided Style-Consistent Content Transfer. In N. Calzolari, M.-Y. Kan, V. Hoste, A. Lenci, S. Sakti, & N. Xue (Hrsg.), 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings (S. 13754-13768)
Chen WF, Alshomary M, Stahl M, Al Khatib K, Stein B, Wachsmuth H. Reference-guided Style-Consistent Content Transfer. in Calzolari N, Kan MY, Hoste V, Lenci A, Sakti S, Xue N, Hrsg., 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings. 2024. S. 13754-13768
Chen, Wei Fan ; Alshomary, Milad ; Stahl, Maja et al. / Reference-guided Style-Consistent Content Transfer. 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings. Hrsg. / Nicoletta Calzolari ; Min-Yen Kan ; Veronique Hoste ; Alessandro Lenci ; Sakriani Sakti ; Nianwen Xue. 2024. S. 13754-13768
Download
@inproceedings{5eabd82f0b194a40a37d013a0f499fbe,
title = "Reference-guided Style-Consistent Content Transfer",
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.",
keywords = "Natural Language Generation, Paraphrasing, Text Analytics, Textual Entailment",
author = "Chen, {Wei Fan} and Milad Alshomary and Maja Stahl and {Al Khatib}, Khalid and Benno Stein and Henning Wachsmuth",
note = "Publisher Copyright: {\textcopyright} 2024 ELRA Language Resource Association: CC BY-NC 4.0.; Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024 ; Conference date: 20-05-2024 Through 25-05-2024",
year = "2024",
language = "English",
pages = "13754--13768",
editor = "Nicoletta Calzolari and Min-Yen Kan and Veronique Hoste and Alessandro Lenci and Sakriani Sakti and Nianwen Xue",
booktitle = "2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings",

}

Download

TY - GEN

T1 - Reference-guided Style-Consistent Content Transfer

AU - Chen, Wei Fan

AU - Alshomary, Milad

AU - Stahl, Maja

AU - Al Khatib, Khalid

AU - Stein, Benno

AU - Wachsmuth, Henning

N1 - Publisher Copyright: © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

PY - 2024

Y1 - 2024

N2 - 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.

AB - 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.

KW - Natural Language Generation

KW - Paraphrasing

KW - Text Analytics

KW - Textual Entailment

UR - http://www.scopus.com/inward/record.url?scp=85195932392&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85195932392

SP - 13754

EP - 13768

BT - 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings

A2 - Calzolari, Nicoletta

A2 - Kan, Min-Yen

A2 - Hoste, Veronique

A2 - Lenci, Alessandro

A2 - Sakti, Sakriani

A2 - Xue, Nianwen

T2 - Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

Y2 - 20 May 2024 through 25 May 2024

ER -

Von denselben Autoren