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

Showing 1120 of 209 papers

TitleStatusHype
ParaFusion: A Large-Scale LLM-Driven English Paraphrase Dataset Infused with High-Quality Lexical and Syntactic Diversity0
Improved Paraphrase Generation via Controllable Latent DiffusionCode0
SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucinationCode0
SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes0
Fine-tuning CLIP Text Encoders with Two-step Paraphrasing0
Neural Machine Translation for Malayalam Paraphrase Generation0
Vector-Quantized Prompt Learning for Paraphrase Generation0
Paraphrase Types for Generation and DetectionCode1
A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase GenerationCode0
Contextual Data Augmentation for Task-Oriented Dialog Systems0
Show:102550
← PrevPage 2 of 21Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HRQ-VAEiBLEU24.93Unverified
2SeparatoriBLEU14.84Unverified
#ModelMetricClaimedVerifiedStatus
1HRQ-VAEiBLEU18.42Unverified
2SeparatoriBLEU5.84Unverified
#ModelMetricClaimedVerifiedStatus
1HRQ-VAEBLEU27.9Unverified