mlsanityData to 14 Oct 2026

Construction of the Literature Graph in Semantic Scholar

arXiv 1805.02262 ↗First posted 6 May 2018cs.CLcited by 118

Not on the map. Why?

Abstract (arXiv)

We describe a deployed scalable system for organizing published scientific literature into a heterogeneous graph to facilitate algorithmic manipulation and discovery. The resulting literature graph consists of more than 280M nodes, representing papers, authors, entities and various interactions between them (e.g., authorships, citations, entity mentions). We reduce literature graph construction into familiar NLP tasks (e.g., entity extraction and linking), point out research challenges due to differences from standard formulations of these tasks, and report empirical results for each task. The methods described in this paper are used to enable semantic features in www.semanticscholar.org

Key facts. Cited by 118 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 34; 2022: 18; 2023: 22; 2024: 17; 2025: 9; 2026: 18.

118 papers.

Sort:

By area:

  1. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 331
  2. 2022Large Language Models are Few-Shot Clinical Information Extractorscited by 207
  3. 2021The Values Encoded in Machine Learning Researchcited by 172
  4. 2022Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editingcited by 166
  5. 2023A Survey of Large Language Models in Medicine: Progress, Application, and Challengecited by 124
  6. 2021Systematic Inequalities in Language Technology Performance across the World's Languagescited by 120
  7. 2023The Semantic Scholar Open Data Platformcited by 118
  8. 2021BERT: A Review of Applications in Natural Language Processing and Understandingcited by 109
  9. 2024A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discoverycited by 96
  10. 2021Time Waits for No One! Analysis and Challenges of Temporal Misalignmentcited by 91
  11. 2021MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extractioncited by 83
  12. 2022BioBART: Pretraining and Evaluation of A Biomedical Generative Language Modelcited by 83
38 more
  1. 2021MS2: Multi-Document Summarization of Medical Studiescited by 80
  2. 2021Including Signed Languages in Natural Language Processingcited by 68
  3. 2021Paragraph-level Simplification of Medical Textscited by 53
  4. 2023mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Modelcited by 32
  5. 2021Relational World Knowledge Representation in Contextual Language Models: A Reviewcited by 31
  6. 2022Performance Optimization for Semantic Communications: An Attention-based Reinforcement Learning Approachcited by 28
  7. 2023Accelerating science with human-aware artificial intelligencecited by 28
  8. 2021VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groupscited by 27
  9. 2023Convolutional Learning on Simplicial Complexescited by 27
  10. 2024Data-Centric Foundation Models in Computational Healthcare: A Surveycited by 27
  11. 2021Boosting Low-Resource Biomedical QA via Entity-Aware Masking Strategiescited by 21
  12. 2021End-to-End NLP Knowledge Graph Constructioncited by 21
  13. 2023CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Datacited by 21
  14. 2021OAG-BERT: Towards A Unified Backbone Language Model For Academic Knowledge Servicescited by 20
  15. 2021Masader: Metadata Sourcing for Arabic Text and Speech Data Resourcescited by 20
  16. 2025SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Taskscited by 20
  17. 2023MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluationcited by 19
  18. 2021CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understandingcited by 17
  19. 2023The Effect of Metadata on Scientific Literature Tagging: A Cross-Field Cross-Model Studycited by 17
  20. 2023Generating a Structured Summary of Numerous Academic Papers: Dataset and Methodcited by 16
  21. 2023Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understandingcited by 16
  22. 2021Trans4E: Link Prediction on Scholarly Knowledge Graphscited by 13
  23. 2021Making Paper Reviewing Robust to Bid Manipulation Attackscited by 12
  24. 2022VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understandingcited by 12
  25. 2023Generation of Highlights from Research Papers Using Pointer-Generator Networks and SciBERT Embeddingscited by 12
  26. 2024Improving Health Question Answering with Reliable and Time-Aware Evidence Retrievalcited by 12
  27. 2024Generative Adversarial Reviews: When LLMs Become the Criticcited by 12
  28. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  29. 2023Evaluation of GPT and BERT-based models on identifying protein-protein interactions in biomedical textcited by 9
  30. 2024TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphscited by 9
  31. 2022Automatic Related Work Generation: A Meta Studycited by 8
  32. 2023Enhancing Biomedical Lay Summarisation with External Knowledge Graphscited by 8
  33. 2024Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistancecited by 8
  34. 2021Linguistically Informed Masking for Representation Learning in the Patent Domaincited by 7
  35. 2021Improving the robustness and accuracy of biomedical language models through adversarial trainingcited by 7
  36. 2023Several categories of Large Language Models (LLMs): A Short Surveycited by 7
  37. 2024On the Detection of Reviewer-Author Collusion Rings From Paper Biddingcited by 7
  38. 2025Serialized EHR make for good text representationscited by 7

50 most cited of 118 All 118 (JSON)