Language as a Latent Variable: Discrete Generative Models for Sentence Compression
Explore this paper's citation graph
Summary
This work forms a variational auto-encoder for inference in a deep generative model of text in which the latent representation of a document is itself drawn from a discrete language model distribution and shows that generative formulations of both abstractive and extractive compression yield state-of-the-art results when trained on a large amount of supervised data.
- Type
- preprint
- Published
- 2016-09-23
- Cited by
- 228
- References
- 50
- Access
- Open access
- OpenAlex
- https://openalex.org/W2526471240
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:10480989
Keywords
Computer science, Latent variable, Generative model, Generative grammar, Latent variable model
References
- Attention-Based Models for Speech Recognition
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Recurrent Continuous Translation Models
- A Neural Attention Model for Abstractive Sentence Summarization
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Auto-Encoding Variational Bayes
- Semi-supervised Learning with Deep Generative Models
- Semi-supervised Sequence Learning
- Generating Sentences from a Continuous Space
- Sentence Compression by Deletion with LSTMs
- Recurrent Neural Network Grammars
- Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations
- Pointer Networks
- Learning internal representations by error propagation
- Sequence to Sequence Learning with Neural Networks
- Recurrent Models of Visual Attention
- DRAW: A Recurrent Neural Network For Image Generation
- Pointing the Unknown Words
- Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
- Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
Cited by
- The Neural Noisy Channel
- Get To The Point: Summarization with Pointer-Generator Networks
- Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
- Recent Advances on Neural Headline Generation
- A Generative Parser with a Discriminative Recognition Algorithm
- Self-organized Hierarchical Softmax
- Deep Recurrent Generative Decoder for Abstractive Text Summarization
- Morphological Inflection Generation with Multi-space Variational Encoder-Decoders
- Semi-supervised Structured Prediction with Neural CRF Autoencoder
- Learning with Latent Language
- A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines
- Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networks
- A multi-level encoder for text summarization
- Incorporating Discriminator in Sentence Generation: a Gibbs Sampling Method
- Natural language generation as neural sequence learning and beyond
- Actor-Critic based Training Framework for Abstractive Summarization
- A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents
- A Stochastic Decoder for Neural Machine Translation
- Multi-Sentence Compression with Word Vertex-Labeled Graphs and Integer Linear Programming
- Incremental generative models for syntactic and semantic natural language processing
Related papers
- TC-VAE: Uncovering Out-of-Distribution Data Generative Factors
- Generative Model for Person Re-Identification: A Review
- Latent Variable Models
- Modeling Configural Patterns in Latent Variable Profiles: Association With an Endogenous Variable
- Nonlinear Effects in the Generalized Latent Variable Model
- Learning a Hierarchical Latent-Variable Model of Voxelized 3D Shapes
- Spectral Latent Variable Models for Perceptual Inference