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 61–67 of 67 papers

TitleStatusHype
Encoder-Agnostic Adaptation for Conditional Language GenerationCode0
Topic-Guided Variational Auto-Encoder for Text Generation—0
Pretraining for Conditional Generation with Pseudo Self Attention—0
Pragmatically Informative Text GenerationCode0
Topic-Guided Variational Autoencoders for Text Generation—0
Conditional Variational Autoencoder for Neural Machine Translation—0
Generating Text through Adversarial Training using Skip-Thought VectorsCode0
Show:102550
← PrevPage 7 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