Unsupervised Paraphrase Generation using Pre-trained Language Models
This addresses the need for unsupervised paraphrase generation to enhance data augmentation in NLP tasks, but it is incremental as it builds on existing pre-trained models.
The paper tackled the problem of generating paraphrases without labeled data by leveraging GPT-2's generation capabilities, resulting in paraphrases of good quality and diversity that improved downstream task performance when used for data augmentation.
Large scale Pre-trained Language Models have proven to be very powerful approach in various Natural language tasks. OpenAI's GPT-2 \cite{radford2019language} is notable for its capability to generate fluent, well formulated, grammatically consistent text and for phrase completions. In this paper we leverage this generation capability of GPT-2 to generate paraphrases without any supervision from labelled data. We examine how the results compare with other supervised and unsupervised approaches and the effect of using paraphrases for data augmentation on downstream tasks such as classification. Our experiments show that paraphrases generated with our model are of good quality, are diverse and improves the downstream task performance when used for data augmentation.