# Extract with Order for Coherent Multi-Document Summarization

arXiv: https://arxiv.org/abs/1706.06542 · HTML: https://mlsanity.com/paper/1706.06542/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2017.

## Built on by (most cited first, 9 of 9)

- [BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP](https://mlsanity.com/paper/2309.13173/) (2023)
- [Unsupervised Abstractive Summarization of Bengali Text Documents](https://mlsanity.com/paper/2102.04490/) (2021)
- [XL-HeadTags: Leveraging Multimodal Retrieval Augmentation for the Multilingual Generation of News Headlines and Tags](https://mlsanity.com/paper/2406.03776/) (2024)
- [Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings](https://mlsanity.com/paper/2110.06446/) (2021)
- [OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews](https://mlsanity.com/paper/2509.00285/) (2025)
- [eC-Tab2Text: Aspect-Based Text Generation from e-Commerce Product Tables](https://mlsanity.com/paper/2502.14820/) (2025)
- [Graph-of-Tweets: A Graph Merging Approach to Sub-event Identification](https://mlsanity.com/paper/2101.03208/) (2021)
- [LFOSum: Summarizing Long-form Opinions with Large Language Models](https://mlsanity.com/paper/2410.13037/) (2024)
- [Multi-Document Keyphrase Extraction: Dataset, Baselines and Review](https://mlsanity.com/paper/2110.01073/) (2021)

## Abstract (arXiv)

In this work, we aim at developing an extractive summarizer in the multi-document setting. We implement a rank based sentence selection using continuous vector representations along with key-phrases. Furthermore, we propose a model to tackle summary coherence for increasing readability. We conduct experiments on the Document Understanding Conference (DUC) 2004 datasets using ROUGE toolkit. Our experiments demonstrate that the methods bring significant improvements over the state of the art methods in terms of informativity and coherence.