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 51–60 of 67 papers

TitleStatusHype
Technical Report: Auxiliary Tuning and its Application to Conditional Text Generation—0
Improving Disentangled Text Representation Learning with Information-Theoretic Guidance—0
Learning Implicit Text Generation via Feature Matching—0
Token Manipulation Generative Adversarial Network for Text GenerationCode0
TextGAIL: Generative Adversarial Imitation Learning for Text Generation—0
CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection—0
Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-EncodersCode0
Improved Variational Neural Machine Translation by Promoting Mutual Information—0
Transfer Reward Learning for Policy Gradient-Based Text Generation—0
Conditional Text Generation for Harmonious Human-Machine Interaction—0
Show:102550
← PrevPage 6 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