Abstract
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.
Highlights
IntroductionRecurrent neural network language models (rnnlms, Mikolov et al, 2011) represent the state of the art in unsupervised generative modeling for natural language sentences
Recurrent neural network language models represent the state of the art in unsupervised generative modeling for natural language sentences
Drawing inspiration from recent successes in modeling images (Gregor et al, 2015), handwriting, and natural speech (Chung et al, 2015), our model circumvents these difficulties using the architecture of a variational autoencoder and takes advantage of recent advances in variational inference (Kingma and Welling, 2015; Rezende et al, 2014) that introduce a practical training technique for powerful neural network generative models with latent variables
Summary
Recurrent neural network language models (rnnlms, Mikolov et al, 2011) represent the state of the art in unsupervised generative modeling for natural language sentences. Rnnlm decoders conditioned on taskspecific features are the state of the art in tasks like machine translation (Sutskever et al, 2014; Bahdanau et al, 2015) and image captioning (Vinyals et al, 2015; Mao et al, 2015; Donahue et al, 2015). The rnnlm generates sentences word-by-word based on an evolving distributed state representation, which makes it a probabilistic model with no significant independence i went to the store to buy some groceries . A standard rnn language model predicts each word of a sentence conditioned on the previous word and an evolving hidden state. While effective, it does not learn a vector representation of the full sentence. In the case of a sequence autoencoder, both encoder and decoder are rnns and examples are token sequences
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
