Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning
This work addresses the problem of generating paraphrases with controlled novelty for NLP applications, presenting an incremental improvement through parameter-efficient and model-agnostic methods.
The paper tackled paraphrase generation by proposing Retrieval Augmented Prompt Tuning (RAPT) for adapting large language models and Novelty Conditioned RAPT (NC-RAPT) for controlled generation with varying lexical novelty, demonstrating effectiveness in retaining semantics while inducing novelty across four datasets.
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.