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 51–60 of 209 papers

TitleStatusHype
An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase GenerationCode0
Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generationCode0
Multilingual Lexical Simplification via Paraphrase GenerationCode0
'John ate 5 apples' != 'John ate some apples': Self-Supervised Paraphrase Quality Detection for Algebraic Word ProblemsCode0
Improving the Diversity of Unsupervised Paraphrasing with Embedding OutputsCode0
Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked DataCode0
Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language ModelsCode0
Action Controlled ParaphrasingCode0
Exemplar-Controllable Paraphrasing and Translation using BitextCode0
Ask me in your own words: paraphrasing for multitask question answeringCode0
Show:102550
← PrevPage 6 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