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 121–130 of 209 papers

TitleStatusHype
Unsupervised Paraphrasability Prediction for Compound Nominalizations—0
Unsupervised Paraphrase Generation using Pre-trained Language Models—0
Unsupervised Paraphrasing with Pretrained Language Models—0
Unsupervised Paraphrasing by Simulated Annealing—0
Unsupervised Paraphrasing via Deep Reinforcement Learning—0
Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations—0
Unsupervised Text Generation by Learning from Search—0
Using character overlap to improve language transformation—0
Using Paraphrases and Lexical Semantics to Improve the Accuracy and the Robustness of Supervised Models in Situated Dialogue Systems—0
Vector-Quantized Prompt Learning for Paraphrase Generation—0
Show:102550
← PrevPage 13 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