mlsanityData to 7 Oct 2026

Natural Language Processing in the Patent Domain: A Survey

arXiv 2403.04105 ↗First posted 6 Mar 2024cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

Patents, which encapsulate crucial technical and legal information in text form and referenced drawings, present a rich domain for natural language processing (NLP) applications. As NLP technologies evolve, large language models (LLMs) have demonstrated outstanding capabilities in general text processing and generation tasks. However, the application of LLMs in the patent domain remains under-explored and under-developed due to the complexity of patents, particularly their language and legal framework. Understanding the unique characteristics of patent documents and related research in the patent domain becomes essential for researchers to apply these tools effectively. Therefore, this paper aims to equip NLP researchers with the essential knowledge to navigate this complex domain efficiently. We introduce the relevant fundamental aspects of patents to provide solid background information. In addition, we systematically break down the structural and linguistic characteristics unique to patents and map out how NLP can be leveraged for patent analysis and generation. Moreover, we demonstrate the spectrum of text-based and multimodal patent-related tasks, including nine patent analysis and four patent generation tasks.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 52 of its 210 references that are in the map. First posted on arXiv 6 Mar 2024.

Builds on

52 of 210 references.

References · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  7. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  8. 2020Scaling Laws for Neural Language Modelscited by 6,411
  9. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  10. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  11. 2020Longformer: The Long-Document Transformercited by 3,362
  12. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
38 more
  1. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  2. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  3. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  4. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  5. 2014Distributed Representations of Sentences and Documentscited by 677
  6. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  7. 2023Effective Long-Context Scaling of Foundation Modelscited by 301
  8. 2019Revealing the Dark Secrets of BERTcited by 300
  9. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 271
  10. 2021LongT5: Efficient Text-To-Text Transformer for Long Sequencescited by 232
  11. 2015The Benefit of Multitask Representation Learningcited by 194
  12. 2019BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarizationcited by 155
  13. 2019Controllable Sentence Simplificationcited by 78
  14. 2023LLMs Accelerate Annotation for Medical Information Extractioncited by 77
  15. 2022Structured information extraction from complex scientific text with fine-tuned large language modelscited by 56
  16. 2019Patent Claim Generation by Fine-Tuning OpenAI GPT-2cited by 49
  17. 2023Natural Language Processing in the Legal Domaincited by 38
  18. 2023RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Modelscited by 36
  19. 2022The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applicationscited by 32
  20. 2021PatentSBERTa: A Deep NLP based Hybrid Model for Patent Distance and Classification using Augmented SBERTcited by 22
  21. 2021Engineering Knowledge Graph from Patent Databasecited by 18
  22. 2017Patent Retrieval: A Literature Reviewcited by 17
  23. 2019TechNet: Technology Semantic Network Based on Patent Datacited by 14
  24. 2020PatentMatch: A Dataset for Matching Patent Claims & Prior Artcited by 14
  25. 2023PatFig: Generating Short and Long Captions for Patent Figurescited by 12
  26. 2019ActiveHNE: Active Heterogeneous Network Embeddingcited by 11
  27. 2021Deep Learning for Technical Document Classificationcited by 11
  28. 2020A Text-Embedding-based Approach to Measure Patent-to-Patent Technological Similarity -- Workflow, Code, and Applicationscited by 8
  29. 2019Automating the search for a patent's prior art with a full text similarity searchcited by 7
  30. 2021Summarization, Simplification, and Generation: The Case of Patentscited by 6
  31. 2022Evaluating Generative Patent Language Modelscited by 6
  32. 2023Event-based Dynamic Graph Representation Learning for Patent Application Trend Predictioncited by 6
  33. 2021Patent Data for Engineering Design: A Critical Review and Future Directionscited by 5
  34. 2022Generative Design Ideation: A Natural Language Generation Approachcited by 5
  35. 2022Enhancing Patent Retrieval using Text and Knowledge Graph Embeddings: A Technical Notecited by 5
  36. 2020Cross-domain Retrieval in the Legal and Patent Domains: a Reproducibility Studycited by 4
  37. 2023Learning Efficient Representations for Image-Based Patent Retrievalcited by 4
  38. 2023Creating a silver standard for patent simplificationcited by 3

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 9; 2026: 7.

20 papers.

Sort:

By area:

  1. 2024Can Large Language Models Generate High-quality Patent Claims?cited by 19
  2. 2024AutoPatent: A Multi-Agent Framework for Automatic Patent Generationcited by 16
  3. 2025Towards Better Evaluation for Generated Patent Claimscited by 8
  4. 2025Enriching Patent Claim Generation with European Patent Datasetcited by 5
  5. 2024Patent-CR: A Dataset for Patent Claim Revisioncited by 4
  6. 2024EvoPat: A Multi-LLM-based Patents Summarization and Analysis Agentcited by 4
  7. 2025Self-Filtered Distillation with LLMs-generated Trust Indicators for Reliable Patent Classificationcited by 4
  8. 2025PatenTEB: A Comprehensive Benchmark and Model Family for Patent Text Embeddingcited by 4
  9. 2025MK2 at PBIG Competition: A Prompt Generation Solutioncited by 3
  10. 2025AutoSpec: An Agentic Framework for Automatically Drafting Patent Specificationcited by 3
  11. 2026FlowPlan-G2P: A Structured Generation Framework for Transforming Scientific Papers into Patent Descriptionscited by 1
  12. 2026Is It Novel and Why? Fine-Grained Patent Novelty Prediction Based on Passage Retrievalcited by 1
8 more
  1. 2025Can Large Language Models Understand As Well As Apply Patent Regulations to Pass a Hands-On Patent Attorney Test?cited by 0
  2. 2025A Hybrid Ai Framework For Strategic Patent Portfolio Pruning: Integrating Learning To-Rank And Market Need Analysis For Technology Transfer Optimizationcited by 0
  3. 2025ERA-IT: Aligning Semantic Models with Revealed Economic Preference for Real-Time and Explainable Patent Valuationcited by 0
  4. 2026Anticipating Innovation Using Large Language Modelscited by 0
  5. 2026Benchmarking Patent Embeddings: A Multi-Task Evaluation of 22 Models Across Retrieval, Classification, and Clusteringcited by 0
  6. 2026Benchmarking Patent Drafting from Inventor-Style Disclosurescited by 0
  7. 2026BLANC: Discovering Patent White Space via Changes in Normalized Pointwise Mutual Information Between Multi-View Clusterscited by 0
  8. 2026LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Draftingcited by 0