文本生成的论文追溯:Seq2seq,VAE,GAN

Seq2seq

《Recent Advances on Neural Headline Generation》 JCST 2017

《A Neural Conversational Model》 ICML 2015

《Topic Aware Neural Response Generation》 AAAI 2017 

《A persona-Based Neural Conversation Model》 ACL 2016

《Incorporating Copying Mechanism in Sequence-to-Sequence Learning》 ACL 2016

《Context-aware Natural Language Generation with Recurrent Neural Networks》 AAAI 2016

《Learning to Generate Product Reviews from Attributes》 EACL 2017

 

VAE:

 

  • 《Generating Sentences From a Continuous Spaces》. ICLR 2016

  • 《Neural Variational Inference for Text Processing》. ICML 2016

  • 《Language as a Latent Variable: Discrete Generative Models for Sentence Compression》. EMNLP 2016

  • 《A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues》. AAAI 2017

 

GAN:

GAN 的首次提出

(Generative adversarial nets[C], 2014.)

GAN最初用于生成文本

(Generating Text via Adversarial Training [J]. 2016)

(Adversarial Feature Matching for Text Generation[J]. 2017.)

VAE+GAN 生成可以控制属性的文本

( Controllable Text Generation[J]. 2017. )

LeakGAN 高效生成长文本

(Long Text Generation via Adversarial Training with Leaked Information[J]. 2018.)

 

你可能感兴趣的:(阅读论文)