Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Explore this paper's citation graph
Summary
This work proposes several novel models that address critical problems in summarization that are not adequately modeled by the basic architecture, such as modeling key-words, capturing the hierarchy of sentence-to-word structure, and emitting words that are rare or unseen at training time.
- Type
- preprint
- Published
- 2016-02-19
- Cited by
- 2,883
- References
- 34
- Access
- Open access
- OpenAlex
- https://openalex.org/W2341401723
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:8928715
Keywords
Automatic summarization, Computer science, Sentence, Recurrent neural network, Natural language processing
References
- ADADELTA: An Adaptive Learning Rate Method
- Title Generation with Quasi-Synchronous Grammar
- Teaching Machines to Read and Comprehend
- A Neural Attention Model for Abstractive Sentence Summarization
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Long story short - Global unsupervised models for keyphrase based meeting summarization
- Headline Generation Based on Statistical Translation
- Graph-Based Keyword Extraction for Single-Document Summarization
- Sentence Compression Beyond Word Deletion
- Self reinforcement for important passage retrieval
- On Using Very Large Target Vocabulary for Neural Machine Translation
- Extractive Summarization Using Supervised and Semi-Supervised Learning
- BBN/UMD at DUC-2004: Topiary
- End-to-end attention-based large vocabulary speech recognition
- LexRank: Graph-based Lexical Centrality as Salience in Text Summarization
- A Hierarchical Neural Autoencoder for Paragraphs and Documents
- Addressing the Rare Word Problem in Neural Machine Translation
- Sequence to Sequence -- Video to Text
- Distributed Representations of Words and Phrases and their Compositionality
- Overcoming the Lack of Parallel Data in Sentence Compression
Cited by
- Natural Language Video Description using Deep Recurrent Neural Networks
- Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling
- From Extractive to Abstractive Summarization: A Journey
- Language as a Latent Variable: Discrete Generative Models for Sentence Compression
- A multi-task learning model for malware classification with useful file access pattern from API call sequence
- Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
- Unsupervised Pretraining for Sequence to Sequence Learning
- A Simple, Fast Diverse Decoding Algorithm for Neural Generation
- Joint Copying and Restricted Generation for Paraphrase
- Neural Headline Generation on Abstract Meaning Representation
- Duplicate Question Detection Using Online Learning
- Efficient Summarization with Read-Again and Copy Mechanism
- OpenNMT: Open-Source Toolkit for Neural Machine Translation
- Classify or Select: Neural Architectures for Extractive Document Summarization
- Learning to Decode for Future Success
- RNN-based Encoder-decoder Approach with Word Frequency Estimation
- Massive Exploration of Neural Machine Translation Architectures
- Recent advances in document summarization
- Get To The Point: Summarization with Pointer-Generator Networks
- Selective Encoding for Abstractive Sentence Summarization
Related papers
- On the Applications of the Experience Summarization in Modern Teaching and Research
- Multilingual Summarization Evaluation without Human Models
- Experiences with and Reflections on Text Summarization Tools
- Dynamic Summarization: Another Stride Towards Summarization
- Efficient Sequence Labeling with Actor-Critic Training
- Convolutional recurrent neural network for question answering
- Word Level LSTM and Recurrent Neural Network for Automatic Text Generation
- Research on Text Summarization Generation Based on LSTM and Attention Mechanism