Generating Sentences from a Continuous Space
This work addresses the challenge of explicit global sentence representation in language generation for natural language processing, though it is incremental as it builds on existing variational autoencoder and RNN methods.
The authors tackled the problem of generating sentences from a continuous latent space by introducing an RNN-based variational autoencoder that models holistic sentence properties, resulting in diverse and well-formed sentences through deterministic decoding and coherent interpolation between known sentences.
The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based variational autoencoder generative model that incorporates distributed latent representations of entire sentences. This factorization allows it to explicitly model holistic properties of sentences such as style, topic, and high-level syntactic features. Samples from the prior over these sentence representations remarkably produce diverse and well-formed sentences through simple deterministic decoding. By examining paths through this latent space, we are able to generate coherent novel sentences that interpolate between known sentences. We present techniques for solving the difficult learning problem presented by this model, demonstrate its effectiveness in imputing missing words, explore many interesting properties of the model's latent sentence space, and present negative results on the use of the model in language modeling.