ConRPG: Paraphrase Generation using Contexts as Regularizer
Yuxian Meng, Xiang Ao, Qing He, Xiaofei Sun, Qinghong Han, Fei Wu, Chun Chieh Fan, Jiwei Li
2021Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing20 citationsDOIOpen Access PDF
Abstract
A long-standing issue with paraphrase generation is how to obtain reliable supervision signals. In this paper, we propose an unsupervised paradigm for paraphrase generation based on the assumption that the probabilities of generating two sentences with the same meaning given the same context should be the same. Inspired by this fundamental idea, we propose a pipelined system which consists of paraphrase candidate generation based on contextual language models, candidate filtering using scoring functions, and paraphrase model training based on the selected candidates.
Topics & Concepts
ParaphraseComputer scienceArtificial intelligenceNatural language processingContext (archaeology)Lexical diversityMeaning (existential)Machine learningLinguisticsPsychologyVocabularyBiologyPsychotherapistPaleontologyPhilosophyTopic ModelingNatural Language Processing TechniquesMultimodal Machine Learning Applications