mlsanityData to 7 Oct 2026

Learning Neural Templates for Text Generation

arXiv 1808.10122 ↗First posted 30 Aug 2018cs.CL cs.LGcited by 61

Not on the map. Why?

Abstract (arXiv)

While neural, encoder-decoder models have had significant empirical success in text generation, there remain several unaddressed problems with this style of generation. Encoder-decoder models are largely (a) uninterpretable, and (b) difficult to control in terms of their phrasing or content. This work proposes a neural generation system using a hidden semi-markov model (HSMM) decoder, which learns latent, discrete templates jointly with learning to generate. We show that this model learns useful templates, and that these templates make generation both more interpretable and controllable. Furthermore, we show that this approach scales to real data sets and achieves strong performance nearing that of encoder-decoder text generation models.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 18; 2023: 13; 2024: 4; 2025: 1; 2026: 1.

61 papers.

Sort:

By area:

  1. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
  2. 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 137
  3. 2021Skill Induction and Planning with Latent Languagecited by 99
  4. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  5. 2021Planning with Learned Entity Prompts for Abstractive Summarizationcited by 75
  6. 2021Plan-then-Generate: Controlled Data-to-Text Generation via Planningcited by 52
  7. 2021Leveraging Language to Learn Program Abstractions and Search Heuristicscited by 44
  8. 2022Conditional Generation with a Question-Answering Blueprintcited by 44
  9. 2021Controlling Hallucinations at Word Level in Data-to-Text Generationcited by 41
  10. 2021What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarizationcited by 35
  11. 2023Benchmarking and Improving Text-to-SQL Generation under Ambiguitycited by 31
  12. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
38 more
  1. 2021Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric Viewcited by 24
  2. 2021Few-Shot Table-to-Text Generation with Prototype Memorycited by 21
  3. 2022Neural Pipeline for Zero-Shot Data-to-Text Generationcited by 19
  4. 2021Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Datacited by 17
  5. 2021BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognitioncited by 15
  6. 2021DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformercited by 14
  7. 2023Towards Verifiable Text Generation with Symbolic Referencescited by 13
  8. 2022Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarizationcited by 12
  9. 2021GenNI: Human-AI Collaboration for Data-Backed Text Generationcited by 11
  10. 2023Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domaincited by 11
  11. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  12. 2024DiffLM: Controllable Synthetic Data Generation via Diffusion Language Modelscited by 9
  13. 2021Search and Learn: Improving Semantic Coverage for Data-to-Text Generationcited by 8
  14. 2023Regeneration Learning: A Learning Paradigm for Data Generationcited by 8
  15. 2021AGGGEN: Ordering and Aggregating while Generatingcited by 7
  16. 2023Automatically Summarizing Evidence from Clinical Trials: A Prototype Highlighting Current Challengescited by 7
  17. 2023LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extractioncited by 7
  18. 2022AutoTemplate: A Simple Recipe for Lexically Constrained Text Generationcited by 6
  19. 2023Improving User Controlled Table-To-Text Generation Robustnesscited by 6
  20. 2023PixT3: Pixel-based Table-To-Text Generationcited by 6
  21. 2022Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shotscited by 5
  22. 2023Sequentially Controlled Text Generationcited by 5
  23. 2021Data-to-text Generation by Splicing Together Nearest Neighborscited by 4
  24. 2021Automatic Document Sketching: Generating Drafts from Analogous Textscited by 4
  25. 2022TempLM: Distilling Language Models into Template-Based Generatorscited by 4
  26. 2022Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognitioncited by 4
  27. 2024A Systematic Review of Data-to-Text NLGcited by 4
  28. 2021Nutribullets Hybrid: Multi-document Health Summarizationcited by 3
  29. 2024Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generationcited by 3
  30. 2021Adversarial Machine Learning in Text Analysis and Generationcited by 2
  31. 2021Scaling Structured Inference with Randomizationcited by 2
  32. 2022Learning with Latent Structures in Natural Language Processing: A Surveycited by 2
  33. 2022Learning to Express in Knowledge-Grounded Conversationcited by 2
  34. 2023Biomembrane-based Memcapacitive Reservoir Computing System for Energy Efficient Temporal Data Processingcited by 2
  35. 2023Automatic Logical Forms improve fidelity in Table-to-Text generationcited by 2
  36. 2024Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Modelcited by 2
  37. 2021Transforming Multi-Conditioned Generation from Meaning Representationcited by 1
  38. 2021There Once Was a Really Bad Poet, It Was Automated but You Didn't Know Itcited by 1

50 most cited of 61 All 61 (JSON)