• Corpus ID: 211171764

Transfer Learning for Abstractive Summarization at Controllable Budgets

@article{Sarkhel2020TransferLF,
  title={Transfer Learning for Abstractive Summarization at Controllable Budgets},
  author={Ritesh Sarkhel and Moniba Keymanesh and Arnab Nandi and Srinivasan Parthasarathy},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.07845}
}
Summarizing a document within an allocated budget while maintaining its major concepts is a challenging task. If the budget can take any arbitrary value and not known beforehand, it becomes even more difficult. Most of the existing methods for abstractive summarization, including state-of-the-art neural networks are data intensive. If the number of available training samples becomes limited, they fail to construct high-quality summaries. We propose MLS, an end-to-end framework to generate… 
2 Citations

Figures and Tables from this paper

MeetSum: Transforming Meeting Transcript Summarization using Transformers!

A qualitative analysis of the summaries generated by the improved Transformer-based Pointer Generator Network shows that these summaries and human-readable and indeed capture most of the important information from the transcripts.

Toward Domain-Guided Controllable Summarization of Privacy Policies

This work proposes a hybrid approach to identify sections of privacy policies with a high privacy risk factor and incorporates these sections into summaries by selecting the riskiest content from different privacy topics using plain English reference summaries.

References

SHOWING 1-10 OF 39 REFERENCES

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.

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.

Abstractive Sentence Summarization with Attentive Recurrent Neural Networks

A conditional recurrent neural network (RNN) which generates a summary of an input sentence which significantly outperforms the recently proposed state-of-the-art method on the Gigaword corpus while performing competitively on the DUC-2004 shared task.

Get To The Point: Summarization with Pointer-Generator Networks

A novel architecture that augments the standard sequence-to-sequence attentional model in two orthogonal ways, using a hybrid pointer-generator network that can copy words from the source text via pointing, which aids accurate reproduction of information, while retaining the ability to produce novel words through the generator.

A Neural Attention Model for Abstractive Sentence Summarization

This work proposes a fully data-driven approach to abstractive sentence summarization by utilizing a local attention-based model that generates each word of the summary conditioned on the input sentence.

Controllable Abstractive Summarization

A neural summarization model with a simple but effective mechanism to enable users to specify high level attributes in order to control the shape of the final summaries to better suit their needs.

Controlling Length in Abstractive Summarization Using a Convolutional Neural Network

This paper proposes an approach to constrain the summary length by extending a convolutional sequence to sequence model, and shows that this approach generates high-quality summaries with user defined length, and outperforms the baselines consistently in terms of ROUGE score, length variations and semantic similarity.

Statistics-Based Summarization - Step One: Sentence Compression

This paper focuses on sentence compression, a simpler version of this larger challenge, and aims to achieve two goals simultaneously: the compressions should be grammatical, and they should retain the most important pieces of information.

Recent advances in document summarization

Significant contributions made in recent years are emphasized, including progress on modern sentence extraction approaches that improve concept coverage, information diversity and content coherence, as well as attempts from summarization frameworks that integrate sentence compression, and more abstractive systems that are able to produce completely new sentences.

Language Modeling with Gated Convolutional Networks

A finite context approach through stacked convolutions, which can be more efficient since they allow parallelization over sequential tokens, is developed and is the first time a non-recurrent approach is competitive with strong recurrent models on these large scale language tasks.