SOTAVerified

Conditional Text Generation

The task of generating text according to some pre-specified conditioning (e.g. topic or sentiment or constraint)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 67 papers

TitleStatusHype
Input-length-shortening and text generation via attention values—0
GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and AugmentationCode1
Reward Gaming in Conditional Text Generation—0
FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training—0
Demonstrating EMMA: Embodied MultiModal Agent for Language-guided Action Execution in 3D Simulated Environments—0
The Dialog Must Go On: Improving Visual Dialog via Generative Self-TrainingCode1
BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in BanglaCode1
AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language ModelingCode1
Regression Transformer: Concurrent sequence regression and generation for molecular language modelingCode1
On the Anatomy of Latent-variable Generative Models for Conditional Text Generation—0
Show:102550
← PrevPage 3 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GPT-2-no-fine-tuningIgnored Constraint Error Rate28.2—Unverified
2GPT-2-fine-tuned-5-epochsIgnored Constraint Error Rate0.5—Unverified
3GPT-2-fine-tuned-20-epochsIgnored Constraint Error Rate0.3—Unverified
4GPT-2-with-filterIgnored Constraint Error Rate0—Unverified