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


  • Hazel H. Kim Yonsei University, Seoul, Republic of Korea NAVER AI Lab
  • Daecheol Woo Yonsei University, Seoul, Republic of Korea
  • Seong Joon Oh Naver AI Lab
  • Jeong-Won Cha Changwon National University, Changwon, Republic of Korea
  • Yo-Sub Han Yonsei University, Seoul, Republic of Korea



Speech & Natural Language Processing (SNLP)


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.




How to Cite

Kim, H. H., Woo, D., Oh, S. J., Cha, J.-W., & Han, Y.-S. (2022). ALP: Data Augmentation Using Lexicalized PCFGs for Few-Shot Text Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 10894-10902.



AAAI Technical Track on Speech and Natural Language Processing