mlsanityData to 7 Oct 2026

AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation

arXiv 2106.05589 ↗First posted 10 Jun 2021cs.CLcited by 17

Not on the map. Why?

Abstract (arXiv)

Natural Language Generation (NLG) is a key component in a task-oriented dialogue system, which converts the structured meaning representation (MR) to the natural language. For large-scale conversational systems, where it is common to have over hundreds of intents and thousands of slots, neither template-based approaches nor model-based approaches are scalable. Recently, neural NLGs started leveraging transfer learning and showed promising results in few-shot settings. This paper proposes AUGNLG, a novel data augmentation approach that combines a self-trained neural retrieval model with a few-shot learned NLU model, to automatically create MR-to-Text data from open-domain texts. The proposed system mostly outperforms the state-of-the-art methods on the FewShotWOZ data in both BLEU and Slot Error Rate. We further confirm improved results on the FewShotSGD data and provide comprehensive analysis results on key components of our system. Our code and data are available at https://github.com/XinnuoXu/AugNLG.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 25 of its 29 references that are in the map. First posted on arXiv 10 Jun 2021.

Builds on

25 of 29 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  4. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,153
  5. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  6. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  7. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  8. 2020MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classificationcited by 186
  9. 2018Neural Approaches to Conversational AIcited by 164
  10. 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
  11. 2019Augmenting Data with Mixup for Sentence Classification: An Empirical Studycited by 125
  12. 2020Self-training Improves Pre-training for Natural Language Understandingcited by 96
13 more
  1. 2020Few-shot Natural Language Generation for Task-Oriented Dialogcited by 89
  2. 2020Continual Learning in Task-Oriented Dialogue Systemscited by 82
  3. 2019A Repository of Conversational Datasetscited by 45
  4. 2019Learning Data Manipulation for Augmentation and Weightingcited by 44
  5. 2020Paraphrase Augmented Task-Oriented Dialog Generationcited by 43
  6. 2019Pre-trained Language Model Representations for Language Generationcited by 34
  7. 2020Schema-Guided Dialogue State Tracking Task at DSTC8cited by 32
  8. 2016Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Stringscited by 27
  9. 2016Multi-domain Neural Network Language Generation for Spoken Dialogue Systemscited by 18
  10. 2019Data Augmentation with Atomic Templates for Spoken Language Understandingcited by 10
  11. 2019Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialoguecited by 7
  12. 2017Neural-based Natural Language Generation in Dialogue using RNN Encoder-Decoder with Semantic Aggregationcited by 6
  13. 2017Natural Language Generation for Spoken Dialogue System using RNN Encoder-Decoder Networkscited by 5

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 4; 2023: 6; 2024: 3; 2025: 2.

17 papers.

Sort:

By area:

  1. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  2. 2021Data Augmentation Approaches in Natural Language Processing: A Surveycited by 82
  3. 2022PromDA: Prompt-based Data Augmentation for Low-Resource NLU Taskscited by 51
  4. 2024A Survey of Data Synthesis Approachescited by 8
  5. 2023Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentationscited by 7
  6. 2024Incubating Text Classifiers Following User Instruction with Nothing but LLMcited by 6
  7. 2025Dual-level Mixup for Graph Few-shot Learning with Fewer Taskscited by 5
  8. 2023Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Rankingcited by 4
  9. 2024DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Modelscited by 3
  10. 2023Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorizationcited by 2
  11. 2023Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialoguescited by 2
  12. 2023Contextual Data Augmentation for Task-Oriented Dialog Systemscited by 2
5 more
  1. 2022Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generationcited by 1
  2. 2022Selective Token Generation for Few-shot Natural Language Generationcited by 1
  3. 2023Compositional Generalization for Data-to-Text Generationcited by 1
  4. 2021Reinforcement Learning for Few-Shot Text Generation Adaptationcited by 0
  5. 2025A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domainscited by 0