Style Transfer as Data Augmentation: A Case Study on Named Entity Recognition
Not on the map. Why?
Abstract (arXiv)
In this work, we take the named entity recognition task in the English language as a case study and explore style transfer as a data augmentation method to increase the size and diversity of training data in low-resource scenarios. We propose a new method to effectively transform the text from a high-resource domain to a low-resource domain by changing its style-related attributes to generate synthetic data for training. Moreover, we design a constrained decoding algorithm along with a set of key ingredients for data selection to guarantee the generation of valid and coherent data. Experiments and analysis on five different domain pairs under different data regimes demonstrate that our approach can significantly improve results compared to current state-of-the-art data augmentation methods. Our approach is a practical solution to data scarcity, and we expect it to be applicable to other NLP tasks.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 46 of its 63 references that are in the map. First posted on arXiv 14 Oct 2022.
Builds on
46 of 63 references.
References · 46
- 2017Attention Is All You Needcited by 60,361
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2015Distilling the Knowledge in a Neural Networkcited by 10,324
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2019The Curious Case of Neural Text Degenerationcited by 2,916
- 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
- 2020Big Bird: Transformers for Longer Sequencescited by 1,684
- 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
- 2018Hierarchical Neural Story Generationcited by 1,193
- 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
34 more
- 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
- 2019Neural Text Generation with Unlikelihood Trainingcited by 503
- 2020Autoregressive Entity Retrievalcited by 334
- 2020LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentioncited by 326
- 2019SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimizationcited by 254
- 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 248
- 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 211
- 2019BPE-Dropout: Simple and Effective Subword Regularizationcited by 195
- 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
- 2020Reformulating Unsupervised Style Transfer as Paraphrase Generationcited by 183
- 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 158
- 2020Better Fine-Tuning by Reducing Representational Collapsecited by 157
- 2021Few-NERD: A Few-Shot Named Entity Recognition Datasetcited by 152
- 2021Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extractioncited by 129
- 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
- 2018Style Transfer Through Back-Translationcited by 124
- 2020An Analysis of Simple Data Augmentation for Named Entity Recognitioncited by 76
- 2018Unsupervised Text Style Transfer using Language Models as Discriminatorscited by 70
- 2020A Probabilistic Formulation of Unsupervised Text Style Transfercited by 70
- 2018Polite Dialogue Generation Without Parallel Datacited by 59
- 2020PowerTransformer: Unsupervised Controllable Revision for Biased Language Correctioncited by 59
- 2017Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Modelscited by 57
- 2019Generalized Data Augmentation for Low-Resource Translationcited by 53
- 2020Local Additivity Based Data Augmentation for Semi-supervised NERcited by 31
- 2018Multi-Task Neural Models for Translating Between Styles Within and Across Languagescited by 28
- 2021RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Modelscited by 28
- 2020On Learning Text Style Transfer with Direct Rewardscited by 24
- 2020Named Entity Recognition for Social Media Texts with Semantic Augmentationcited by 23
- 2021Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decodingcited by 23
- 2022Transforming Sequence Tagging Into A Seq2Seq Taskcited by 15
- 2021Data Augmentation for Cross-Domain Named Entity Recognitioncited by 14
- 2021GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognitioncited by 12
- 2018Label-aware Double Transfer Learning for Cross-Specialty Medical Named Entity Recognitioncited by 9
- 2019Robustness to Capitalization Errors in Named Entity Recognitioncited by 5
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 1.
2 papers.