Document Summarization

46 papers with code · Natural Language Processing
Subtask of Text Summarization

Leaderboards

Latest papers with code

StructSum: Incorporating Latent and Explicit Sentence Dependencies for Single Document Summarization

1 Mar 2020atulkum/pointer_summarizer

Traditional preneural approaches to single document summarization relied on modeling the intermediate structure of a document before generating the summary.

DOCUMENT SUMMARIZATION

441
01 Mar 2020

On Extractive and Abstractive Neural Document Summarization with Transformer Language Models

7 Sep 2019Bread-and-Code/Text-Summarization

We present a method to produce abstractive summaries of long documents that exceed several thousand words via neural abstractive summarization.

ABSTRACTIVE TEXT SUMMARIZATION DOCUMENT SUMMARIZATION LANGUAGE MODELLING

15
07 Sep 2019

Mixture Content Selection for Diverse Sequence Generation

IJCNLP 2019 clovaai/FocusSeq2Seq

The diversification stage uses a mixture of experts to sample different binary masks on the source sequence for diverse content selection.

ABSTRACTIVE TEXT SUMMARIZATION DOCUMENT SUMMARIZATION QUESTION GENERATION

69
04 Sep 2019

Text Summarization with Pretrained Encoders

IJCNLP 2019 nlpyang/PreSumm

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).

 SOTA for Extractive Document Summarization on CNN / Daily Mail (using extra training data)

ABSTRACTIVE TEXT SUMMARIZATION DOCUMENT SUMMARIZATION EXTRACTIVE DOCUMENT SUMMARIZATION

500
22 Aug 2019

Learning towards Abstractive Timeline Summarization

IJCAI 2019 2019 yingtaomj/Learning-towards-Abstractive-Timeline-Summarization

Timeline summarization targets at concisely summarizing the evolution trajectory along the timeline and existing timeline summarization approaches are all based on extractive methods. In this paper, we propose the task of abstractive timeline summarization, which tends to concisely paraphrase the information in the time-stamped events. Unlike traditional document summarization, timeline summarization needs to model the time series information of the input events and summarize important events in chronological order. To tackle this challenge, we propose a memory-based timeline summarization model (MTS). Concretely, we propose a time-event memory to establish a timeline, and use the time position of events on this timeline to guide generation process. Besides, in each decoding step, we incorporate event-level information into word-level attention to avoid confusion between events. Extensive experiments are conducted on a large-scale real-world dataset, and the results show that MTS achieves the state-of-the-art performance in terms of both automatic and human evaluations.

DOCUMENT SUMMARIZATION TIMELINE SUMMARIZATION TIME SERIES

3
11 Aug 2019

Overview and Results: CL-SciSumm Shared Task 2019

23 Jul 2019WING-NUS/scisumm-corpus

All papers are from the open access research papers in the CL domain.

DOCUMENT SUMMARIZATION INFORMATION RETRIEVAL

116
23 Jul 2019

Sentence Centrality Revisited for Unsupervised Summarization

ACL 2019 mswellhao/PacSum

Single document summarization has enjoyed renewed interests in recent years thanks to the popularity of neural network models and the availability of large-scale datasets.

DOCUMENT SUMMARIZATION REPRESENTATION LEARNING

43
08 Jun 2019