# ALP: Data Augmentation using Lexicalized PCFGs for Few-Shot Text Classification

arXiv: https://arxiv.org/abs/2112.11916 · HTML: https://mlsanity.com/paper/2112.11916/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 16 Dec 2021.

## Builds on (most cited first, 16 of 16)

- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels](https://mlsanity.com/paper/1905.05040/) (2019)
- [MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification](https://mlsanity.com/paper/2004.12239/) (2020)
- [Data Augmentation using Pre-trained Transformer Models](https://mlsanity.com/paper/2003.02245/) (2020)
- [QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension](https://mlsanity.com/paper/1804.09541/) (2018)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness](https://mlsanity.com/paper/2009.10195/) (2020)
- [SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup](https://mlsanity.com/paper/2010.02322/) (2020)
- [How Important is the Train-Validation Split in Meta-Learning?](https://mlsanity.com/paper/2010.05843/) (2020)
- [Is Support Set Diversity Necessary for Meta-Learning?](https://mlsanity.com/paper/2011.14048/) (2020)
- [HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning](https://mlsanity.com/paper/1904.07633/) (2019)
- [A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning](https://mlsanity.com/paper/2106.15615/) (2021)

## Built on by (most cited first, 10 of 10)

- [Neighborhood-Regularized Self-Training for Learning with Few Labels](https://mlsanity.com/paper/2301.03726/) (2023)
- [Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better](https://mlsanity.com/paper/2402.00263/) (2024)
- [ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions](https://mlsanity.com/paper/2406.04286/) (2024)
- [From Big to Small Without Losing It All: Text Augmentation with ChatGPT for Efficient Sentiment Analysis](https://mlsanity.com/paper/2312.04720/) (2023)
- [An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classification](https://mlsanity.com/paper/2409.03203/) (2024)
- [Targeted Augmentation for Low-Resource Event Extraction](https://mlsanity.com/paper/2405.08729/) (2024)
- [BootAug: Boosting Text Augmentation via Hybrid Instance Filtering Framework](https://mlsanity.com/paper/2210.02941/) (2022)
- [Simple Data Augmentation Techniques for Chinese Disease Normalization](https://mlsanity.com/paper/2306.01931/) (2023)
- [Feature Weaken: Vicinal Data Augmentation for Classification](https://mlsanity.com/paper/2211.10944/) (2022)
- [Evaluation Metrics for Text Data Augmentation in NLP](https://mlsanity.com/paper/2402.06766/) (2024)

## Abstract (arXiv)

Data augmentation has been an important ingredient for boosting performances of learned models. Prior data augmentation methods for few-shot text classification have led to great performance boosts. However, they have not been designed to capture the intricate compositional structure of natural language. As a result, they fail to generate samples with plausible and diverse sentence structures. Motivated by this, we present the data Augmentation using Lexicalized Probabilistic context-free grammars (ALP) that generates augmented samples with diverse syntactic structures with plausible grammar. The lexicalized PCFG parse trees consider both the constituents and dependencies to produce a syntactic frame that maximizes a variety of word choices in a syntactically preservable manner without specific domain experts. Experiments on few-shot text classification tasks demonstrate that ALP enhances many state-of-the-art classification methods. As a second contribution, we delve into the train-val splitting methodologies when a data augmentation method comes into play. We argue empirically that the traditional splitting of training and validation sets is sub-optimal compared to our novel augmentation-based splitting strategies that further expand the training split with the same number of labeled data. Taken together, our contributions on the data augmentation strategies yield a strong training recipe for few-shot text classification tasks.