# Iterative Document Representation Learning Towards Summarization with Polishing

arXiv: https://arxiv.org/abs/1809.10324 · HTML: https://mlsanity.com/paper/1809.10324/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2018.

## Built on by (most cited first, 12 of 12)

- [DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents](https://mlsanity.com/paper/2101.11796/) (2021)
- [Align and Attend: Multimodal Summarization with Dual Contrastive Losses](https://mlsanity.com/paper/2303.07284/) (2023)
- [Towards Improving Faithfulness in Abstractive Summarization](https://mlsanity.com/paper/2210.01877/) (2022)
- [Target-aware Abstractive Related Work Generation with Contrastive Learning](https://mlsanity.com/paper/2205.13339/) (2022)
- [Controllable Summarization with Constrained Markov Decision Process](https://mlsanity.com/paper/2108.03405/) (2021)
- [MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos](https://mlsanity.com/paper/2306.04216/) (2023)
- [MHMS: Multimodal Hierarchical Multimedia Summarization](https://mlsanity.com/paper/2204.03734/) (2022)
- [Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment](https://mlsanity.com/paper/2210.04722/) (2022)
- [Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order](https://mlsanity.com/paper/2301.00867/) (2023)
- [Neural Abstractive Unsupervised Summarization of Online News Discussions](https://mlsanity.com/paper/2106.03953/) (2021)
- [A Condense-then-Select Strategy for Text Summarization](https://mlsanity.com/paper/2106.10468/) (2021)
- [Write Summary Step-by-Step: A Pilot Study of Stepwise Summarization](https://mlsanity.com/paper/2406.05361/) (2024)

## Abstract (arXiv)

In this paper, we introduce Iterative Text Summarization (ITS), an iteration-based model for supervised extractive text summarization, inspired by the observation that it is often necessary for a human to read an article multiple times in order to fully understand and summarize its contents. Current summarization approaches read through a document only once to generate a document representation, resulting in a sub-optimal representation. To address this issue we introduce a model which iteratively polishes the document representation on many passes through the document. As part of our model, we also introduce a selective reading mechanism that decides more accurately the extent to which each sentence in the model should be updated. Experimental results on the CNN/DailyMail and DUC2002 datasets demonstrate that our model significantly outperforms state-of-the-art extractive systems when evaluated by machines and by humans.