Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Ramesh Nallapati low, Bowen Zhou, Cícero dos Santos low, Çağlar Gülçehre, Bing Xiang
In this work, we model abstractive text summarization using Attentional Encoder-Decoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora. We propose 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-toword structure, and emitting words that are rare or unseen at training time. Our work shows that many of our proposed models contribute to further improvement in performance. We also propose a new dataset consisting of multi-sentence summaries, and establish performance benchmarks for further research.
Citation edge evidence
- Get To The Point: Summarization with Pointer-Generator Networks→Abstractive Text Summarization using Sequence-to-sequence RNNs and BeyondLegacy edge — source detail unavailable
- fairseq: A Fast, Extensible Toolkit for Sequence Modeling→Abstractive Text Summarization using Sequence-to-sequence RNNs and BeyondLegacy edge — source detail unavailable
- Convolutional Sequence to Sequence Learning→Abstractive Text Summarization using Sequence-to-sequence RNNs and BeyondLegacy edge — source detail unavailable
- Text Summarization with Pretrained Encoders→Abstractive Text Summarization using Sequence-to-sequence RNNs and BeyondLegacy edge — source detail unavailable
- Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond→Neural Machine Translation by Jointly Learning to Align and TranslateLegacy edge — source detail unavailable
- Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond→ADADELTA: An Adaptive Learning Rate MethodLegacy edge — source detail unavailable
- Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond→Natural Language Processing (almost) from ScratchLegacy edge — source detail unavailable
- Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond→Teaching Machines to Read and ComprehendLegacy edge — source detail unavailable
- Neural Machine Translation by Jointly Learning to Align and Translate→ADADELTA: An Adaptive Learning Rate MethodLegacy edge — source detail unavailable
- Get To The Point: Summarization with Pointer-Generator Networks→Neural Machine Translation by Jointly Learning to Align and TranslateLegacy edge — source detail unavailable
- Get To The Point: Summarization with Pointer-Generator Networks→Teaching Machines to Read and ComprehendLegacy edge — source detail unavailable
- fairseq: A Fast, Extensible Toolkit for Sequence Modeling→Get To The Point: Summarization with Pointer-Generator NetworksLegacy edge — source detail unavailable
- fairseq: A Fast, Extensible Toolkit for Sequence Modeling→Convolutional Sequence to Sequence LearningLegacy edge — source detail unavailable
- fairseq: A Fast, Extensible Toolkit for Sequence Modeling→Teaching Machines to Read and ComprehendLegacy edge — source detail unavailable
- Text Summarization with Pretrained Encoders→Get To The Point: Summarization with Pointer-Generator NetworksLegacy edge — source detail unavailable
- Text Summarization with Pretrained Encoders→Teaching Machines to Read and ComprehendLegacy edge — source detail unavailable
What this paper cites, inside the corpus
| Paper | Year | Cited |
|---|---|---|
| Neural Machine Translation by Jointly Learning to Align and Translate | 2014 | 14,615 |
| ADADELTA: An Adaptive Learning Rate Method | 2012 | 5,532 |
| Natural Language Processing (almost) from Scratch | 2011 | 3,991 |
| Teaching Machines to Read and Comprehend | 2015 | 1,939 |
What cites it, inside the corpus
Links
Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record
Topics
| Topic Modeling | Computer Science |
| Natural Language Processing Techniques | Computer Science |
| Advanced Text Analysis Techniques | Computer Science |
Is this record sound?
complete
Nothing in this record contradicts itself and no field we check is missing.
- supports5 author record(s) attached.
- supports34 reference(s) recorded.
- neutralThe DOI carries no year to check against.
- supportsA title is present.
Provenance
sha256 86a6d6715ff540a0…