mlsanityData to 7 Oct 2026

LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training

arXiv 2112.01404 ↗First posted 2 Dec 2021cs.CL cs.AI cs.IRcited by 5

Not on the map. Why?

Abstract (arXiv)

Natural language generation from structured data mainly focuses on surface-level descriptions, suffering from uncontrollable content selection and low fidelity. Previous works leverage logical forms to facilitate logical knowledge-conditioned text generation. Though achieving remarkable progress, they are data-hungry, which makes the adoption for real-world applications challenging with limited data. To this end, this paper proposes a unified framework for logical knowledge-conditioned text generation in the few-shot setting. With only a few seeds logical forms (e.g., 20/100 shot), our approach leverages self-training and samples pseudo logical forms based on content and structure consistency. Experimental results demonstrate that our approach can obtain better few-shot performance than baselines.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 36 of its 60 references that are in the map. First posted on arXiv 2 Dec 2021.

Builds on

36 of 60 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  6. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  7. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
  8. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
  9. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  10. 2021KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extractioncited by 180
  11. 2016Dual Learning for Machine Translationcited by 146
  12. 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
24 more
  1. 2020Self-training Improves Pre-training for Natural Language Understandingcited by 96
  2. 2020Logical Natural Language Generation from Open-Domain Tablescited by 90
  3. 2019Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challengecited by 86
  4. 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
  5. 2019Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networkscited by 61
  6. 2018A Graph-to-Sequence Model for AMR-to-Text Generationcited by 56
  7. 2017Table-to-text Generation by Structure-aware Seq2seq Learningcited by 54
  8. 2019Few-Shot NLG with Pre-Trained Language Modelcited by 52
  9. 2020Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraintscited by 48
  10. 2020Logic2Text: High-Fidelity Natural Language Generation from Logical Formscited by 45
  11. 2020GPT-too: A language-model-first approach for AMR-to-text generationcited by 38
  12. 2021AliCG: Fine-grained and Evolvable Conceptual Graph Construction for Semantic Search at Alibabacited by 33
  13. 2020Text Classification Using Label Names Only: A Language Model Self-Training Approachcited by 32
  14. 2018Natural Language Generation for Electronic Health Recordscited by 27
  15. 2020Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondencecited by 25
  16. 2019Relation Adversarial Network for Low Resource Knowledge Graph Completioncited by 24
  17. 2021Structural Information Preserving for Graph-to-Text Generationcited by 24
  18. 2021OntoED: Low-resource Event Detection with Ontology Embeddingcited by 23
  19. 2021SentiPrompt: Sentiment Knowledge Enhanced Prompt-Tuning for Aspect-Based Sentiment Analysiscited by 23
  20. 2019Structural Neural Encoders for AMR-to-text Generationcited by 19
  21. 2019Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time)cited by 18
  22. 2021Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embeddingcited by 18
  23. 2020DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Toolcited by 12
  24. 2019Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Datacited by 6

Built on by

Cited by year

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

5 papers.

  1. 2022OntoProtein: Protein Pretraining With Gene Ontology Embeddingcited by 70
  2. 2022Ontology-enhanced Prompt-tuning for Few-shot Learningcited by 24
  3. 2022DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Populationcited by 17
  4. 2022Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual Samplescited by 1
  5. 2024Self-training from Self-memory in Data-to-text Generationcited by 0