Adversarial Feature Matching for Text Generation

The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We propose a framework for generating realistic text via adversarial training. We employ a long short-term memory network as generator, and a convolutional network as discriminator. Instead of using the standard objective of GAN, we propose matching the high-dimensional latent feature distributions of real and synthetic sentences, via a kernelized discrepancy metric. This eases adversarial training by alleviating the mode-collapsing problem. Our experiments show superior performance in quantitative evaluation, and demonstrate that our model can generate realistic-looking sentences.

[1]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[2]  Alan Ritter,et al.  Adversarial Learning for Neural Dialogue Generation , 2017, EMNLP.

[3]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[4]  Ole Winther,et al.  Autoencoding beyond pixels using a learned similarity metric , 2015, ICML.

[5]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[6]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[7]  Léon Bottou,et al.  Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[8]  E. Gumbel.  Statistical Theory of Extreme Values and Some Practical Applications : A Series of Lectures , 1954 .

[9]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[10]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[11]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[12]  Tong Zhang,et al.  Effective Use of Word Order for Text Categorization with Convolutional Neural Networks , 2014, NAACL.

[13]  Ferenc Huszar,et al.  How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary? , 2015, ArXiv.

[14]  Yee Whye Teh,et al.  The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables , 2016, ICLR.

[15]  Ben Poole,et al.  Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.

[16]  Zhe Gan,et al.  Variational Autoencoder for Deep Learning of Images, Labels and Captions , 2016, NIPS.

[17]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[18]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.

[19]  Phil Blunsom,et al.  A Convolutional Neural Network for Modelling Sentences , 2014, ACL.

[20]  Sebastian Nowozin,et al.  f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization , 2016, NIPS.

[21]  Zoubin Ghahramani,et al.  Training generative neural networks via Maximum Mean Discrepancy optimization , 2015, UAI.

[22]  Razvan Pascanu,et al.  Theano: new features and speed improvements , 2012, ArXiv.

[23]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[24]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[25]  Yann LeCun,et al.  Energy-based Generative Adversarial Network , 2016, ICLR.

[26]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[27]  Lantao Yu,et al.  SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient , 2016, AAAI.

[28]  Zhe Gan,et al.  Generating Text via Adversarial Training , 2016 .

[29]  Richard S. Zemel,et al.  Generative Moment Matching Networks , 2015, ICML.

[30]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[31]  Hang Li,et al.  Convolutional Neural Network Architectures for Matching Natural Language Sentences , 2014, NIPS.

[32]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[33]  David Pfau,et al.  Unrolled Generative Adversarial Networks , 2016, ICLR.

[34]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[35]  Samy Bengio,et al.  Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks , 2015, NIPS.

[36]  Barnabás Póczos,et al.  On the High-dimensional Power of Linear-time Kernel Two-Sample Testing under Mean-difference Alternatives , 2014, ArXiv.

[37]  Sebastian Nowozin,et al.  Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks , 2017, ICML.

[38]  Bernhard Schölkopf,et al.  A Kernel Two-Sample Test , 2012, J. Mach. Learn. Res..

[39]  Yoshua Bengio,et al.  Professor Forcing: A New Algorithm for Training Recurrent Networks , 2016, NIPS.

[40]  Jianfeng Gao,et al.  Deep Reinforcement Learning for Dialogue Generation , 2016, EMNLP.

[41]  Zhe Gan,et al.  Learning Generic Sentence Representations Using Convolutional Neural Networks , 2016, EMNLP.

[42]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[43]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[44]  Dilin Wang,et al.  Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning , 2016, ArXiv.

[45]  Sanja Fidler,et al.  Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[46]  Matthias Bethge,et al.  A note on the evaluation of generative models , 2015, ICLR.

[47]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[48]  Samy Bengio,et al.  Generating Sentences from a Continuous Space , 2015, CoNLL.

[49]  Zhe Gan,et al.  Unsupervised Learning of Sentence Representations using Convolutional Neural Networks , 2016, ArXiv.

[50]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[51]  Qiang Liu,et al.  A Kernelized Stein Discrepancy for Goodness-of-fit Tests , 2016, ICML.