SMCLM prepends a frozen sentence embedding to GPT-2 and trains with causal language modeling, producing paraphrases that the authors find competitive with supervised methods and best among the unsupervised baselines tested.
Unsupervised Paraphrase Generation using Pre-trained Language Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SMCLM: Semantically Meaningful Causal Language Modeling for Autoregressive Paraphrase Generation
SMCLM prepends a frozen sentence embedding to GPT-2 and trains with causal language modeling, producing paraphrases that the authors find competitive with supervised methods and best among the unsupervised baselines tested.