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 181–190 of 209 papers

TitleStatusHype
Lost in Translationese? Reducing Translation Effect Using Abstract Meaning RepresentationCode0
Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel DataCode0
Syntactically Robust Training on Partially-Observed Data for Open Information ExtractionCode0
Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked DataCode0
Improved Paraphrase Generation via Controllable Latent DiffusionCode0
An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase GenerationCode0
Multilingual Lexical Simplification via Paraphrase GenerationCode0
Discriminating between Lexico-Semantic Relations with the Specialization Tensor ModelCode0
Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generationCode0
PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data AugmentationCode0
Show:102550
← PrevPage 19 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