Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5493–5500 June 6–11, 2021. ©2021 Association for Computational Linguistics 5493 Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning Jason Wei Chengyu Huang Soroush Vosoughi Yu Cheng Shiqi Xu ProtagoLabs International Monetary Fund Dartmouth College Microsoft AI {jason,xu}@protagolabs.com huangchengyu24@gmail.com soroush@dartmouth.edu yu.cheng@microsoft.com Abstract Few-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category. This paper explores data augmentation—a technique particularly suitable for training with limited data—for this few-shot, highly- multiclass text classification setting. On four diverse text classification tasks, we find that common data augmentation techniques can im- prove the performance of triplet networks by up to 3.0% on average. To further boost performance, we present a simple training strategy called curriculum data augmentation, which leverages curricu- lum learning by first training on only origi- nal examples and then introducing augmented data as training progresses. We explore a two- stage and a gradual schedule, and find that, compared with standard single-stage training, curriculum data augmentation trains faster, im- proves performance, and remains robust to high amounts of noising from augmentation. 1 Introduction Traditional text classification tasks such as senti- ment classification (Socher et al., 2013) typically have few output classes (e.g., in binary classifica- tion), each with many training examples. Many practical scenarios such as relation classification (Han et al., 2018), answer selection (Kumar et al., 2019), and sentence clustering (Mnasri et al., 2017), however, have a converse setup characterized by a large number of output classes (Gupta et al., 2014), often with few training examples per class. This scenario, which we henceforth refer to as few-shot, highly-multiclass text classification, is a common setting in NLP applications and can be challenging due to the scarcity of training data. Data augmentation for NLP has seen increased interest in recent years (Wei and Zou, 2019; Qiu Figure 1: Schematic showing the two types of curricu- lum augmentation that we propose. τ is a parameter that controls augmentation temperature (fraction of per- turbed tokens). et al., 2020). In traditional text classification tasks, it has been shown that although performance im- provements can be marginal when training data is sufficient, augmentation is especially beneficial in limited data scenarios (Xie et al., 2020). As such, we hypothesize that the few-shot, highly-multiclass text classification scenario is a suitable context for data augmentation. Based on this motivation, our paper makes two main contributions. • First, we apply popular data augmentation tech- niques to the common triplet loss (Schroff et al., 2015) approach for few-shot, highly multiclass classification, finding that out-of-the-box aug- mentation can improve performance noticeably. • We then propose a simple curriculum learning strategy called curriculum data augmentation and experiment with two schedules, as shown in Figure 1. A two-stage curriculum, which first trains on original data and then introduces aug- 5494 mented data of …

Content truncated to 500 words