mlsanityData to 7 Oct 2026

Enhancing Scientific Papers Summarization with Citation Graph

arXiv 2104.03057 ↗First posted 7 Apr 2021cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

Previous work for text summarization in scientific domain mainly focused on the content of the input document, but seldom considering its citation network. However, scientific papers are full of uncommon domain-specific terms, making it almost impossible for the model to understand its true meaning without the help of the relevant research community. In this paper, we redefine the task of scientific papers summarization by utilizing their citation graph and propose a citation graph-based summarization model CGSum which can incorporate the information of both the source paper and its references. In addition, we construct a novel scientific papers summarization dataset Semantic Scholar Network (SSN) which contains 141K research papers in different domains and 661K citation relationships. The entire dataset constitutes a large connected citation graph. Extensive experiments show that our model can achieve competitive performance when compared with the pretrained models even with a simple architecture. The results also indicates the citation graph is crucial to better understand the content of papers and generate high-quality summaries.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 22 of its 35 references that are in the map. First posted on arXiv 7 Apr 2021.

Builds on

22 of 35 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  4. 2015Teaching Machines to Read and Comprehendcited by 1,039
  5. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
  6. 2019Text Summarization with Pretrained Encoderscited by 553
  7. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
  8. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  9. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 364
  10. 2016SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documentscited by 245
  11. 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 241
  12. 2020Extractive Summarization as Text Matchingcited by 189
10 more
  1. 2019Text Generation from Knowledge Graphs with Graph Transformerscited by 122
  2. 2020Heterogeneous Graph Neural Networks for Extractive Document Summarizationcited by 90
  3. 2019ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networkscited by 73
  4. 2020Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Rewardcited by 66
  5. 2019Extractive Summarization of Long Documents by Combining Global and Local Contextcited by 59
  6. 2018A Graph-to-Sequence Model for AMR-to-Text Generationcited by 56
  7. 2018Structured Neural Summarizationcited by 53
  8. 2019Searching for Effective Neural Extractive Summarization: What Works and What's Nextcited by 38
  9. 2017Scientific document summarization via citation contextualization and scientific discoursecited by 12
  10. 2020Enhancing Factual Consistency of Abstractive Summarizationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 4; 2023: 4; 2024: 1; 2025: 0; 2026: 1.

14 papers.

Sort:

By area:

  1. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 363
  2. 2024A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methodscited by 101
  3. 2023mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Modelcited by 31
  4. 2021SciXGen: A Scientific Paper Dataset for Context-Aware Text Generationcited by 22
  5. 2021RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarizationcited by 19
  6. 2022Robust Knowledge Adaptation for Dynamic Graph Neural Networkscited by 9
  7. 2023Improving Biomedical Abstractive Summarisation with Knowledge Aggregation from Citation Paperscited by 9
  8. 2022COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarizationcited by 8
  9. 2023A Topic-aware Summarization Framework with Different Modal Side Informationcited by 6
  10. 2022Scientific Paper Extractive Summarization Enhanced by Citation Graphscited by 5
  11. 2021GraphPrompt: Graph-Based Prompt Templates for Biomedical Synonym Predictioncited by 2
  12. 2022Improving Graph-Based Text Representations with Character and Word Level N-gramscited by 2
2 more
  1. 2026COMPOSE: Composing Future Theorems from Citations and Formal Structurecited by 2
  2. 2023Adversarial Conversational Shaping for Intelligent Agentscited by 0