A General Contextualized Rewriting Framework for Text Summarization

Guangsheng Bao, Yue Zhang
7/13/2022
cs.CL

No official code found. Best implementation: baoguangsheng/bart-rewriters (13 stars, MIT, last commit 2022-07-17).

Abstract

The rewriting method for text summarization combines extractive and abstractive approaches, improving the conciseness and readability of extractive summaries using an abstractive model. Exiting rewriting systems take each extractive sentence as the only input, which is relatively focused but can lose necessary background knowledge and discourse context. In this paper, we investigate contextualized rewriting, which consumes the entire document and considers the summary context. We formalize contextualized rewriting as a seq2seq with group-tag alignments, introducing group-tag as a solution to model the alignments, identifying extractive sentences through content-based addressing. Results show that our approach significantly outperforms non-contextualized rewriting systems without requiring reinforcement learning, achieving strong improvements on ROUGE scores upon multiple extractors.

View on arXivView PDF

Code Implementations(1)

baoguangsheng/bart-rewritersCommunity100%
MIT

Code base for "A General Contextualized Rewriting Framework for Text Summarization"

131C++, CudaJun 17, 20224 years agoMIT

Similar Papers

GEMINI: Controlling the Sentence-level Writing Style for Abstractive Text Summarization

85% match1 repo92023

Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback

81% match2023

LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction

81% match2023

Optimizing Abstractive Summarization With Fine-Tuned PEGASUS

81% match2026

RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation

81% match1 repo1492026

Extractive Summarization via ChatGPT for Faithful Summary Generation

81% match2023

Cite this paper

@article{bao2022general,
  title  = {A General Contextualized Rewriting Framework for Text Summarization},
  author = {Guangsheng Bao and Yue Zhang},
  year   = {2022},
  eprint = {2207.05948},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.05948v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.05948.svg)](https://codeofpaper.com/paper/2207.05948)

Discussion