papers AI Learner
The Github is limit! Click to go to the new site.

Unsupervised Paraphrasing without Translation

2019-05-29
Aurko Roy, David Grangier

Abstract

Paraphrasing exemplifies the ability to abstract semantic content from surface forms. Recent work on automatic paraphrasing is dominated by methods leveraging Machine Translation (MT) as an intermediate step. This contrasts with humans, who can paraphrase without being bilingual. This work proposes to learn paraphrasing models from an unlabeled monolingual corpus only. To that end, we propose a residual variant of vector-quantized variational auto-encoder. We compare with MT-based approaches on paraphrase identification, generation, and training augmentation. Monolingual paraphrasing outperforms unsupervised translation in all settings. Comparisons with supervised translation are more mixed: monolingual paraphrasing is interesting for identification and augmentation; supervised translation is superior for generation.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.12752

PDF

http://arxiv.org/pdf/1905.12752


Comments

Content