SOTAVerified

Paraphrase Generation

Paraphrase Generation involves transforming a natural language sentence to a new sentence, that has the same semantic meaning but a different syntactic or lexical surface form.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 111–120 of 209 papers

TitleStatusHype
A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning—0
A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation—0
Latent Template Induction with Gumbel-CRFsCode1
Generative Pre-training for Paraphrase Generation by Representing and Predicting Spans in Exemplars—0
Sound Natural: Content Rephrasing in Dialog SystemsCode0
Paraphrase Generation via Adversarial Penalizations—0
DivGAN: Towards Diverse Paraphrase Generation via Diversified Generative Adversarial Network—0
Gradient-guided Unsupervised Lexically Constrained Text Generation—0
Unsupervised Paraphrasing with Pretrained Language Models—0
Neural-Driven Multi-criteria Tree Search for Paraphrase Generation—0
Show:102550
← PrevPage 12 of 21Next →
All datasetsParalexQuora Question PairsMSCOCO

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HRQ-VAEiBLEU24.93—Unverified
2SeparatoriBLEU14.84—Unverified
#ModelMetricClaimedVerifiedStatus
1HRQ-VAEiBLEU18.42—Unverified
2SeparatoriBLEU5.84—Unverified
#ModelMetricClaimedVerifiedStatus
1HRQ-VAEBLEU27.9—Unverified