Boosting Few-Shot Text Classification via Distribution Estimation

Authors: Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Fenglong Ma, Xiao-Ming Wu, Hongyang Chen, Hong Yu, Xianchao Zhang

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on eight few-shot text classification datasets show that the proposed method outperforms state-of-the-art baselines significantly.
Researcher Affiliation Academia 1 Dalian University of Technology, Dalian, China 2 Peking University, Beijing, China 3 The Pennsylvania State University, Pennsylvania, USA 4 The Hong Kong Polytechnic University, Hong Kong, China 5 Zhejiang Lab, Hangzhou, China
Pseudocode No The paper describes algorithmic steps in prose and mathematical formulas but does not include any clearly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code No The paper does not contain any explicit statements or links indicating that source code for the described methodology is publicly available.
Open Datasets Yes We follow (Chen et al. 2022) to conduct experiments on eight text classification datasets, including four intent detection datasets: Banking77, HWU64, Clinic150, and Liu57, and four news or review classification datasets: Huff Post, Amazon, Reuters, and 20News.
Dataset Splits Yes All reported results are from 5 different runs, and in each run the training, validation and testing classes are randomly resampled.
Hardware Specification No The paper does not specify any particular hardware components (e.g., GPU models, CPU types, memory) used for running the experiments.
Software Dependencies No The paper mentions using 'bert-base-uncased model' and 'Adam W' optimizer but does not specify version numbers for these or other critical software dependencies like Python, PyTorch, or TensorFlow.
Experiment Setup Yes We set R = 10 for the news or review classification task, while R = 4 for the intent detection task. For the loss function, we set λ = 0.1, and optimize the model parameters using Adam W (Loshchilov and Hutter 2019) with the initial learning rate 0.00001 and dropout rate 0.1. During distribution sampling, in 1-shot and 5-shot scenarios, we generate 20 and 100 samples per class respectively.