Linguistically-Controlled Paraphrase Generation

Mohamed Elgaar, Hadi Amiri


Abstract
Controlled paraphrase generation produces paraphrases that preserve meaning while allowing precise control over linguistic attributes of the output. We introduce LingConv, an encoder-decoder framework that enables fine-grained control over 40 linguistic attributes in English. To improve reliability, we introduce a novel inference-time quality control mechanism that iteratively refines attribute embeddings to generate paraphrases that closely match target attributes without sacrificing semantic fidelity. LingConv reduces attribute error by up to 34% over existing models, with the quality control mechanism contributing an additional 14% improvement.
Anthology ID:
2025.findings-emnlp.1137
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
20842–20864
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.1137/
DOI:
Bibkey:
Cite (ACL):
Mohamed Elgaar and Hadi Amiri. 2025. Linguistically-Controlled Paraphrase Generation. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 20842–20864, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Linguistically-Controlled Paraphrase Generation (Elgaar & Amiri, Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.1137.pdf
Checklist:
 2025.findings-emnlp.1137.checklist.pdf