Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings |
| Herausgeber/-innen | Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue |
| Seiten | 13754-13768 |
| Seitenumfang | 15 |
| ISBN (elektronisch) | 9782493814104 |
| Publikationsstatus | Veröffentlicht - 2024 |
| Veranstaltung | Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024 - Hybrid, Torino, Italien Dauer: 20 Mai 2024 → 25 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
- Mathematik (insg.)
- Theoretische Informatik
- Informatik (insg.)
- Theoretische Informatik und Mathematik
- Informatik (insg.)
- Angewandte Informatik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
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/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
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 -