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 1–50 of 209 papers

TitleStatusHype
Latent Template Induction with Gumbel-CRFsCode1
Aspect Sentiment Quad Prediction as Paraphrase GenerationCode1
Syntax-guided Controlled Generation of ParaphrasesCode1
Automatic Compilation of Resources for Academic Writing and Evaluating with Informal Word Identification and Paraphrasing SystemCode1
iNLTK: Natural Language Toolkit for Indic LanguagesCode1
Findings of the The RuATD Shared Task 2022 on Artificial Text Detection in RussianCode1
Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation ApproachCode1
Simultaneous Translation and Paraphrase for Language EducationCode1
Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process PriorsCode1
Language Invariant Properties in Natural Language ProcessingCode1
TESS: Text-to-Text Self-Conditioned Simplex DiffusionCode1
Neural Paraphrase Generation with Stacked Residual LSTM NetworksCode1
Hierarchical Sketch Induction for Paraphrase GenerationCode1
A Deep Generative Framework for Paraphrase GenerationCode1
Generating Syntactically Controlled Paraphrases without Using Annotated Parallel PairsCode1
Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus ExplorationCode1
Reformulating Unsupervised Style Transfer as Paraphrase GenerationCode1
On the Evaluation Metrics for Paraphrase GenerationCode1
How Large Language Models are Transforming Machine-Paraphrased PlagiarismCode1
Towards Document-Level Paraphrase Generation with Sentence Rewriting and ReorderingCode1
Neural semi-Markov CRF for Monolingual Word AlignmentCode1
AESOP: Paraphrase Generation with Adaptive Syntactic ControlCode1
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defenseCode1
kNN-BOX: A Unified Framework for Nearest Neighbor GenerationCode1
Chinese Idiom ParaphrasingCode1
CoEdIT: Text Editing by Task-Specific Instruction TuningCode1
Paraphrase Types for Generation and DetectionCode1
Neural Syntactic Preordering for Controlled Paraphrase GenerationCode1
Paraphrase Generation with Latent Bag of WordsCode1
Paraphrase Generation as Zero-Shot Multilingual Translation: Disentangling Semantic Similarity from Lexical and Syntactic DiversityCode1
A large-scale computational study of content preservation measures for text style transfer and paraphrase generationCode1
Factorising Meaning and Form for Intent-Preserving ParaphrasingCode1
Explicit Syntactic Guidance for Neural Text GenerationCode1
ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase GenerationCode1
Contrastive Representation Learning for Exemplar-Guided Paraphrase GenerationCode1
Quality Controlled Paraphrase GenerationCode1
A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase GenerationCode0
A Large-Scale Benchmark for Vietnamese Sentence ParaphrasesCode0
ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-TranslationCode0
ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model RobustnessCode0
Discriminating between Lexico-Semantic Relations with the Specialization Tensor ModelCode0
Building a Non-Trivial Paraphrase Corpus Using Multiple Machine Translation SystemsCode0
Multilingual Lexical Simplification via Paraphrase GenerationCode0
Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language ModelsCode0
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
Improving the Diversity of Unsupervised Paraphrasing with Embedding OutputsCode0
Improving Non-autoregressive Generation with Mixup TrainingCode0
'John ate 5 apples' != 'John ate some apples': Self-Supervised Paraphrase Quality Detection for Algebraic Word ProblemsCode0
Learning Semantic Sentence Embeddings using Sequential Pair-wise DiscriminatorCode0
Show:102550
← PrevPage 1 of 5Next →
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