Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning

Authors

  • Jishnu Ray Chowdhury Department of Computer Science, University of Illinois at Chicago
  • Yong Zhuang Bloomberg
  • Shuyi Wang Bloomberg

DOI:

https://doi.org/10.1609/aaai.v36i10.21297

Keywords:

Speech & Natural Language Processing (SNLP)

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.

Downloads

Published

2022-06-28

How to Cite

Chowdhury, J. R., Zhuang, Y., & Wang, S. (2022). Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 10535-10544. https://doi.org/10.1609/aaai.v36i10.21297

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing