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 31–40 of 209 papers

TitleStatusHype
Lost in Translationese? Reducing Translation Effect Using Abstract Meaning RepresentationCode0
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defenseCode1
kNN-BOX: A Unified Framework for Nearest Neighbor GenerationCode1
Coherence and Diversity through Noise: Self-Supervised Paraphrase Generation via Structure-Aware Denoising—0
Syntactically Robust Training on Partially-Observed Data for Open Information ExtractionCode0
Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generationCode0
Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations—0
Fine-Grained Emotional Paraphrasing along Emotion Gradients—0
Revision for Concision: A Constrained Paraphrase Generation Task—0
Metaphorical Paraphrase Generation: Feeding Metaphorical Language Models with Literal Texts—0
Show:102550
← PrevPage 4 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