Document Summarization
188 papers with code • 6 benchmarks • 28 datasets
Automatic Document Summarization is the task of rewriting a document into its shorter form while still retaining its important content. The most popular two paradigms are extractive approaches and abstractive approaches. Extractive approaches generate summaries by extracting parts of the original document (usually sentences), while abstractive methods may generate new words or phrases which are not in the original document.
Benchmarks
These leaderboards are used to track progress in Document Summarization
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Document Summarization models and implementationsDatasets
CNN/Daily Mail
NEWSROOM
Multi-News
New York Times Annotated Corpus
WikiSum
WikiLingua
arXiv
WCEP
BookSum
Most implemented papers
Get To The Point: Summarization with Pointer-Generator Networks
abisee/pointer-generator
•
•
ACL 2017
Neural sequence-to-sequence models have provided a viable new approach for abstractive text summarization (meaning they are not restricted to simply selecting and rearranging passages from the original text).
Text Summarization with Pretrained Encoders
nlpyang/PreSumm
•
•
IJCNLP 2019
For abstractive summarization, we propose a new fine-tuning schedule which adopts different optimizers for the encoder and the decoder as a means of alleviating the mismatch between the two (the former is pretrained while the latter is not).
Language Models are Unsupervised Multitask Learners
openai/gpt-2
•
•
Preprint 2019
Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.
Unified Language Model Pre-training for Natural Language Understanding and Generation
microsoft/unilm
•
•
NeurIPS 2019
This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks.
GLM: General Language Model Pretraining with Autoregressive Blank Infilling
On a wide range of tasks across NLU, conditional and unconditional generation, GLM outperforms BERT, T5, and GPT given the same model sizes and data, and achieves the best performance from a single pretrained model with 1. 25x parameters of BERT Large , demonstrating its generalizability to different downstream tasks.
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
kedz/nnsum
•
•
We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to state-of-the-art.
Bottom-Up Abstractive Summarization
We use this selector as a bottom-up attention step to constrain the model to likely phrases.
Generating Wikipedia by Summarizing Long Sequences
tensorflow/tensor2tensor
•
•
ICLR 2018
We show that generating English Wikipedia articles can be approached as a multi- document summarization of source documents.
Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization
shashiongithub/XSum
•
•
EMNLP 2018
We introduce extreme summarization, a new single-document summarization task which does not favor extractive strategies and calls for an abstractive modeling approach.
Scoring Sentence Singletons and Pairs for Abstractive Summarization
ucfnlp/summarization-sing-pair-mix
•
•
ACL 2019
There is thus a crucial gap between sentence selection and fusion to support summarizing by both compressing single sentences and fusing pairs.
