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

Showing 111–120 of 209 papers

TitleStatusHype
Towards Better Characterization of ParaphrasesCode0
Paraphrase Generation as Unsupervised Machine Translation—0
ConRPG: Paraphrase Generation using Contexts as Regularizer—0
SPMoE: Generate Multiple Pattern-Aware Outputs with Sparse Pattern Mixture of Experts—0
Keep the Primary, Rewrite the Secondary: A Two-Stage Approach for Paraphrase Generation—0
Edit Distance Based Curriculum Learning for Paraphrase Generation—0
Neural-Driven Search-Based Paraphrase Generation—0
Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning—0
Delexicalized Paraphrase Generation—0
A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning—0
Show:102550
← PrevPage 12 of 21Next →

Benchmark Results

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