Work

Unsupervised Paraphrasing without Translation

Year: 2019
Type: conference-paper
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.
Language: English
Open Access status: hybrid
OpenAlex ID: W2947465697
FWCI: 3.682
Cites: 51
Cited by: 75
Related to: 10