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
A large-scale computational study of content preservation measures for text style transfer and paraphrase generationCode1
Factorising Meaning and Form for Intent-Preserving ParaphrasingCode1
Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process PriorsCode1
Neural semi-Markov CRF for Monolingual Word AlignmentCode1
Contrastive Representation Learning for Exemplar-Guided Paraphrase GenerationCode1
Paraphrase Generation with Latent Bag of WordsCode1
A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase GenerationCode0
Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language ModelsCode0
'John ate 5 apples' != 'John ate some apples': Self-Supervised Paraphrase Quality Detection for Algebraic Word ProblemsCode0
A Large-Scale Benchmark for Vietnamese Sentence ParaphrasesCode0
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