Learning to Selectively Learn for Weakly-supervised Paraphrase Generation

TL;DR

This paper introduces a novel weakly-supervised approach for paraphrase generation that leverages pseudo paraphrase expansion and meta-learning to select valuable samples, significantly improving over existing unsupervised methods.

Contribution

It proposes a new framework combining pseudo paraphrase expansion and meta-learning for weakly-supervised paraphrase generation, achieving performance comparable to supervised methods.

Findings

Significant improvement over existing unsupervised approaches

Performance comparable to supervised state-of-the-art methods

Effective sample selection via meta-learning enhances paraphrase quality

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.