Unsupervised Paraphrasing by Simulated Annealing

TL;DR

This paper introduces UPSA, an unsupervised method for paraphrase generation using simulated annealing, optimizing semantic similarity, diversity, and fluency without needing parallel data, and achieving state-of-the-art results.

Contribution

The paper presents a novel unsupervised approach for paraphrasing based on simulated annealing, which does not require parallel corpora and outperforms existing methods.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Outperforms many supervised models in generalizability.

Effective in diverse domains without domain-specific training.

Abstract

Unsupervised paraphrase generation is a promising and important research topic in natural language processing. We propose UPSA, a novel approach that accomplishes Unsupervised Paraphrasing by Simulated Annealing. We model paraphrase generation as an optimization problem and propose a sophisticated objective function, involving semantic similarity, expression diversity, and language fluency of paraphrases. Then, UPSA searches the sentence space towards this objective by performing a sequence of local editing. Our method is unsupervised and does not require parallel corpora for training, so it could be easily applied to different domains. We evaluate our approach on a variety of benchmark datasets, namely, Quora, Wikianswers, MSCOCO, and Twitter. Extensive results show that UPSA achieves the state-of-the-art performance compared with previous unsupervised methods in terms of both automatic and human evaluations. Further, our approach outperforms most existing domain-adapted supervised models, showing the generalizability of UPSA.