# SgSum: Transforming Multi-document Summarization into Sub-graph Selection

arXiv: https://arxiv.org/abs/2110.12645 · HTML: https://mlsanity.com/paper/2110.12645/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 53 references that are in the map.
- First posted on arXiv 25 Oct 2021.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies](https://mlsanity.com/paper/1804.11283/) (2018)
- [SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents](https://mlsanity.com/paper/1611.04230/) (2016)
- [Extractive Summarization as Text Matching](https://mlsanity.com/paper/2004.08795/) (2020)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Ranking Sentences for Extractive Summarization with Reinforcement Learning](https://mlsanity.com/paper/1802.08636/) (2018)
- [Discourse-Aware Neural Extractive Text Summarization](https://mlsanity.com/paper/1910.14142/) (2019)
- [Heterogeneous Graph Neural Networks for Extractive Document Summarization](https://mlsanity.com/paper/2004.12393/) (2020)
- [Leveraging Graph to Improve Abstractive Multi-Document Summarization](https://mlsanity.com/paper/2005.10043/) (2020)
- [Graph-based Neural Multi-Document Summarization](https://mlsanity.com/paper/1706.06681/) (2017)
- [Deep Communicating Agents for Abstractive Summarization](https://mlsanity.com/paper/1803.10357/) (2018)
- [Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization](https://mlsanity.com/paper/1808.06218/) (2018)
- [Pretraining-Based Natural Language Generation for Text Summarization](https://mlsanity.com/paper/1902.09243/) (2019)
- [Summary Level Training of Sentence Rewriting for Abstractive Summarization](https://mlsanity.com/paper/1909.08752/) (2019)
- [Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization](https://mlsanity.com/paper/1906.00072/) (2019)
- [BASS: Boosting Abstractive Summarization with Unified Semantic Graph](https://mlsanity.com/paper/2105.12041/) (2021)
- [Graph-based Neural Sentence Ordering](https://mlsanity.com/paper/1912.07225/) (2019)
- [Structure-Infused Copy Mechanisms for Abstractive Summarization](https://mlsanity.com/paper/1806.05658/) (2018)
- [Improving Multi-Document Summarization via Text Classification](https://mlsanity.com/paper/1611.09238/) (2016)
- [Jointly Extracting and Compressing Documents with Summary State Representations](https://mlsanity.com/paper/1904.02020/) (2019)
- [Multi-Document Summarization via Discriminative Summary Reranking](https://mlsanity.com/paper/1507.02062/) (2015)

## Built on by (most cited first, 8 of 8)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization](https://mlsanity.com/paper/2305.13091/) (2023)
- [FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations](https://mlsanity.com/paper/2204.06508/) (2022)
- [EDU-level Extractive Summarization with Varying Summary Lengths](https://mlsanity.com/paper/2210.04029/) (2022)
- [Knowledge-aware Document Summarization: A Survey of Knowledge, Embedding Methods and Architectures](https://mlsanity.com/paper/2204.11190/) (2022)
- [Building Knowledge-Grounded Dialogue Systems with Graph-Based Semantic Modeling](https://mlsanity.com/paper/2204.12681/) (2022)
- [A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization](https://mlsanity.com/paper/2305.08503/) (2023)
- [Vietnamese multi-document summary using subgraph selection approach -- VLSP 2022 AbMuSu Shared Task](https://mlsanity.com/paper/2306.14827/) (2023)

## Abstract (arXiv)

Most of existing extractive multi-document summarization (MDS) methods score each sentence individually and extract salient sentences one by one to compose a summary, which have two main drawbacks: (1) neglecting both the intra and cross-document relations between sentences; (2) neglecting the coherence and conciseness of the whole summary. In this paper, we propose a novel MDS framework (SgSum) to formulate the MDS task as a sub-graph selection problem, in which source documents are regarded as a relation graph of sentences (e.g., similarity graph or discourse graph) and the candidate summaries are its sub-graphs. Instead of selecting salient sentences, SgSum selects a salient sub-graph from the relation graph as the summary. Comparing with traditional methods, our method has two main advantages: (1) the relations between sentences are captured by modeling both the graph structure of the whole document set and the candidate sub-graphs; (2) directly outputs an integrate summary in the form of sub-graph which is more informative and coherent. Extensive experiments on MultiNews and DUC datasets show that our proposed method brings substantial improvements over several strong baselines. Human evaluation results also demonstrate that our model can produce significantly more coherent and informative summaries compared with traditional MDS methods. Moreover, the proposed architecture has strong transfer ability from single to multi-document input, which can reduce the resource bottleneck in MDS tasks. Our code and results are available at: urlhttps://github.com/PaddlePaddle/Research/tree/master/NLP/EMNLP2021-SgSum.