Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning
Abstract
Paraphrase generation is a fundamental and long-standing task in natural language processing. In this paper, we concentrate on two contributions to the task: (1) we propose Retrieval Augmented Prompt Tuning (RAPT) as a parameter-efficient method to adapt large pre-trained language models for paraphrase generation; (2) we propose Novelty Conditioned RAPT (NC-RAPT) as a simple model-agnostic method of using specialized prompt tokens for controlled paraphrase generation with varying levels of lexical novelty. By conducting extensive experiments on four datasets, we demonstrate the effectiveness of the proposed approaches for retaining the semantic content of the original text while inducing lexical novelty in the generation.
Cite
Text
Chowdhury et al. "Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I10.21297Markdown
[Chowdhury et al. "Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/chowdhury2022aaai-novelty/) doi:10.1609/AAAI.V36I10.21297BibTeX
@inproceedings{chowdhury2022aaai-novelty,
title = {{Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning}},
author = {Chowdhury, Jishnu Ray and Zhuang, Yong and Wang, Shuyi},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2022},
pages = {10535-10544},
doi = {10.1609/AAAI.V36I10.21297},
url = {https://mlanthology.org/aaai/2022/chowdhury2022aaai-novelty/}
}