Сохранение Семантики

AbstractWe propose to control paraphrase generation through carefully chosen target syntactic structures to generate more proper and higher quality paraphrases. Our model, AESOP, leverages a pretrained language model and adds …...

AbstractWe propose a method for generating paraphrases of English questions that retain the original intent but use a different surface form. Our model combines a careful choice of training objective …...

In recent years, neural paraphrase generation based on Seq2Seq has achieved superior per- formance, however, the generated paraphrase still has the problem of lack of diversity. In this paper, we …...