Jointly Extracting and Compressing Documents with Summary State Representations

  title={Jointly Extracting and Compressing Documents with Summary State Representations},
  author={Afonso Mendes and Shashi Narayan and Sebasti{\~a}o Miranda and Zita Marinho and Andr{\'e} F. T. Martins and Shay B. Cohen},
We present a new neural model for text summarization that first extracts sentences from a document and then compresses them. The pro-posed model offers a balance that sidesteps thedifficulties in abstractive methods while gener-ating more concise summaries than extractivemethods. In addition, our model dynamically determines the length of the output summary based on the gold summaries it observes during training and does not require length constraints typical to extractive summarization. The… 

Neural Extractive Text Summarization with Syntactic Compression

This work presents a neural model for single-document summarization based on joint extraction and syntactic compression that outperforms an off-the-shelf compression module, and human and manual evaluation shows that the model’s output generally remains grammatical.

On Extractive and Abstractive Neural Document Summarization with Transformer Language Models

A simple extractive step is performed before generating a summary, which is then used to condition the transformer language model on relevant information before being tasked with Generating a summary.

About ? Extreme Summarization with Topic-Aware Convolutional Neural Networks

  • Shashi Narayan
  • Computer Science
  • 2019
This work introduces extreme summarization, a new single-document summarization task which aims at creating a short, one-sentence news summary answering the question “What is the article about?” and proposes a novel abstractive model which is conditioned on the article’s topics and based entirely on convolutional neural networks.

An Attentional Extractive Summarization Framework

This paper proposes a general framework for extractive summarization, the Attentional Extractive Summarization framework, and evaluates two different systems, formalized under the proposed framework, on the CNN/DailyMail and the NewsRoom corpora, which are some of the reference corpora in the most relevant works in text summarization.

What is this Article about? Extreme Summarization with Topic-aware Convolutional Neural Networks

A novel abstractive model is proposed which is conditioned on the article's topics and based entirely on convolutional neural networks, outperforming an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans on the extreme summarization dataset.

Abstractive Document Summarization with Word Embedding Reconstruction

The assumption that inverse document frequency (IDF) measures how important a word is is further leverage the IDF weights in the embedding-level reconstructor and lead to promising improvements for ROUGE metrics and human rating on both the CNN/Daily Mail and Newsroom summarization datasets.

EASE: Extractive-Abstractive Summarization End-to-End using the Information Bottleneck Principle

EASE is proposed, an Extractive-abstractive framework that generates concise abstractive summaries that can be traced back to an extractive summary and is shown that the generated summaries are better than strong extractive and extractive-ABstractive baselines.

EASE: Extractive-Abstractive Summarization with Explanations

This work presents an explainable summarization system based on the Information Bottleneck principle that is jointly trained for extraction and abstraction in an end-to-end fashion and shows that explanations from this framework are more relevant than simple baselines, without substantially sacrificing the quality of the generated summary.

Abstractive Summarization Guided by Latent Hierarchical Document Structure

A hierarchy-aware graph neural network (HierGNN) which captures such dependencies through three main steps: learning a hierarchical document structure through a latent structure tree learned by a sparse matrix-tree computation; propagating sentence information over this structure using a novel message-passing node propagation mechanism to identify salient information.

Copy or Rewrite: Hybrid Summarization with Hierarchical Reinforcement Learning

This work proposes HySum, a hybrid framework for summarization that can flexibly switch between copying sentence and rewriting sentence according to the degree of redundancy, and proposes an end-to-end reinforcing method to bridge together the extraction module and rewriting module, which can enhance the cooperation between them.



Jointly Learning to Extract and Compress

A joint model of sentence extraction and compression for multi-document summarization and its jointly extracted and compressed summaries outperform both unlearned baselines and the authors' learned extraction-only system on both ROUGE and Pyramid, without a drop in judged linguistic quality.

Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization

A novel abstractive model is proposed which is conditioned on the article’s topics and based entirely on convolutional neural networks, outperforming an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans.

Classify or Select: Neural Architectures for Extractive Document Summarization

Two novel and contrasting Recurrent Neural Network (RNN) based architectures for extractive summarization of documents are presented and the models under both architectures jointly capture the notions of salience and redundancy of sentences.

Neural Summarization by Extracting Sentences and Words

This work develops a general framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor that allows for different classes of summarization models which can extract sentences or words.

Abstractive Document Summarization with a Graph-Based Attentional Neural Model

A novel graph-based attention mechanism in the sequence-to-sequence framework to address the saliency factor of summarization, which has been overlooked by prior works and is competitive with state-of-the-art extractive methods.

Bottom-Up Abstractive Summarization

This work explores the use of data-efficient content selectors to over-determine phrases in a source document that should be part of the summary, and shows that this approach improves the ability to compress text, while still generating fluent summaries.

Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

An accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively to generate a concise overall summary is proposed, which achieves the new state-of-the-art on all metrics on the CNN/Daily Mail dataset, as well as significantly higher abstractiveness scores.

Neural Latent Extractive Document Summarization

A latent variable extractive model, where sentences are viewed as latent variables and sentences with activated variables are used to infer gold summaries, which outperforms a strong extractive baseline trained on rule-based labels and performs competitively with several recent models.

A Deep Reinforced Model for Abstractive Summarization

A neural network model with a novel intra-attention that attends over the input and continuously generated output separately, and a new training method that combines standard supervised word prediction and reinforcement learning (RL) that produces higher quality summaries.

Ranking Sentences for Extractive Summarization with Reinforcement Learning

This paper conceptualize extractive summarization as a sentence ranking task and proposes a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective.