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 151–160 of 209 papers

TitleStatusHype
Exploring Diverse Expressions for Paraphrase Generation—0
An End-to-End Generative Architecture for Paraphrase Generation—0
Generating Paraphrases with Lean Vocabulary—0
Towards Diverse Paraphrase Generation Using Multi-Class Wasserstein GAN—0
PNAT: Non-autoregressive Transformer by Position Learning—0
Unsupervised Paraphrasing by Simulated Annealing—0
An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase GenerationCode0
Polly Want a Cracker: Analyzing Performance of Parroting on Paraphrase Generation Datasets—0
A Paraphrase Generation System for EHR Question Answering—0
Generating Sentences from Disentangled Syntactic and Semantic SpacesCode0
Show:102550
← PrevPage 16 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