Learning to Selectively Learn for Weakly-supervised Paraphrase Generation

Abstract

Paraphrase generation is a longstanding NLP task that has diverse applications for downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised endeavors have been proposed to address this issue, they may fail to generate meaningful paraphrases due to the lack of supervision signals. In this work, we go beyond the existing paradigms and propose a novel approach to generate high-quality paraphrases with weak supervision data. Specifically, we tackle the weakly-supervised paraphrase generation problem by: (1) obtaining abundant weakly-labeled parallel sentences via retrieval-based pseudo paraphrase expansion; and (2) developing a meta-learning framework to progressively select valuable samples for fine-tuning a pre-trained language model, i.e., BART, on the sentential paraphrasing task. We demonstrate that our approach achieves significant improvements over existing unsupervised approaches, and is even comparable in performance with supervised state-of-the-arts.

arXiv commentAccepted by EMNLP 2021 (long)

References in corpus (8)

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Neural Paraphrase Generation with Stacked Residual LSTM Networks
• Reinforcement Learning for Relation Classification from Noisy Data
• A Retrieve-and-Edit Framework for Predicting Structured Outputs
• CoaCor: Code Annotation for Code Retrieval with Reinforcement Learning
• Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
• Denoising Multi-Source Weak Supervision for Neural Text Classification
• Paraphrase Generation with Latent Bag of Words