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 91–100 of 209 papers

TitleStatusHype
Learning to Selectively Learn for Weakly-supervised Paraphrase Generation—0
Towards Better Characterization of ParaphrasesCode0
Towards Document-Level Paraphrase Generation with Sentence Rewriting and ReorderingCode1
Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus ExplorationCode1
Paraphrase Generation as Unsupervised Machine Translation—0
Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation ApproachCode1
Contrastive Representation Learning for Exemplar-Guided Paraphrase GenerationCode1
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
Show:102550
← PrevPage 10 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