paper-with-me

홈 › Papers

Generating Sentences from a Continuous Space

2015-11-19 · CONLL 2016 8 · Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew M. Dai, Rafal Jozefowicz, Samy Bengio

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.

📄 PDF Abstract BibTeX arXiv:1511.06349

Code (17)

Chung-I/Variational-Recurrent-Autoencoder-Tensorflow tf
GiuliaLanzillotta/exercises tf
NicGian/text_VAE tf
PaddlePaddle/PaddleNLP/tree/develop/examples/text_generation/vae-seq2seq paddle
StijnVerdenius/Boosting_Text_Classifiers_by_Generative_Modelling pytorch
aaronbae/ModifiedSentenceVAE pytorch
arvind385801/paraphrasegen pytorch
clutr/clutr pytorch
isabelline/Text_VAE_tf tf
jmtomczak/vae_householder_flow
kefirski/pytorch_RVAE pytorch
pranjalg96/Stylized-Image-captioning pytorch
ryokamoi/original_textvae tf
sindhusweety/VAE-Generating-Sentences-From-a-Continuous-Space pytorch
timbmg/Sentence-VAE pytorch
twairball/keras_lstm_vae
wiseodd/controlled-text-generation pytorch

Tasks

Language ModelingLanguage ModellingSentence

Similar Papers 제목 키워드 기반

Generating Sentences from Disentangled Syntactic and Semantic Spaces

2019-07-06 · ACL 2019 7 · Yu Bao, Hao Zhou, Shu-Jian Huang, Lei LI 외

Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model the …

Paraphrase GenerationText Generation

In Search for Linear Relations in Sentence Embedding Spaces

2019-10-08 · Petra Barančíková, Ondřej Bojar

We present an introductory investigation into continuous-space vector representations of sentences. We acquire pairs of very similar sentences differing only by a small alterations (such as change of a noun, adding an ad…

Natural Language InferenceSentenceSentence EmbeddingSentence-Embedding

Language coverage and generalization in RNN-based continuous sentence embeddings for interacting agents

2019-11-05 · Luca Celotti, Simon Brodeur, Jean Rouat

Continuous sentence embeddings using recurrent neural networks (RNNs), where variable-length sentences are encoded into fixed-dimensional vectors, are often the main building blocks of architectures applied to language t…

Dialogue GenerationSentenceSentence Embeddings

Structuring Latent Spaces for Stylized Response Generation

2019-09-03 · IJCNLP 2019 11 · Xiang Gao, Yizhe Zhang, Sungjin Lee, Michel Galley 외

Generating responses in a targeted style is a useful yet challenging task, especially in the absence of parallel data. With limited data, existing methods tend to generate responses that are either less stylized or less …

Response GenerationStyle Transfer

Generating Contradictory, Neutral, and Entailing Sentences

2018-03-07 · Yikang Shen, Shawn Tan, Chin-wei Huang, Aaron Courville

Learning distributed sentence representations remains an interesting problem in the field of Natural Language Processing (NLP). We want to learn a model that approximates the conditional latent space over the representat…

DiversityNatural Language InferenceRTESentence