@inproceedings{62bc99356120496396a081a8d964ae57,
title = "PK-BERT: Knowledge Enhanced Pre-trained Models with Prompt for Few-Shot Learning",
abstract = "The amount of data in some fields are scarce because they are difficult or expensive to obtain. The general practice is to pre-train a model on similar data sets and fine-tune the models in downstream tasks by transfer learning. The pre-trained models could learn the general language representation from large-scale corpora but their downstream task may be different from the pre-trained tasks in form and type. It also lacks related semantic knowledge. Therefore, we propose PK-BERT—Knowledge Enhanced Pre-trained Models with Prompt for Few-shot Learning. It (1) achieves few-shot learning by using small samples with pre-trained models; (2) constructs the prefix that contains the masked label to shorten the gap between downstream task and pre-trained task; (3) uses the explicit representation to inject knowledge graph triples into the text to enhance the sentence information; and (4) uses masked language modelling (MLM) head to convert the classification task into generation task. The experiments show that our proposed model PK-BERT achieves better results.",
keywords = "Few-shot learning, Knowledge graph, Masked language modelling, Pre-trained models, Prompt",
author = "Han Ma and Ng, {Benjamin K.} and Lam, {Chan Tong}",
note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 22nd IEEE/ACIS International Conference on Computer and Information Science, ICIS 2022 ; Conference date: 26-06-2022 Through 28-06-2022",
year = "2023",
doi = "10.1007/978-3-031-12127-2_2",
language = "English",
isbn = "9783031121265",
series = "Studies in Computational Intelligence",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "31--44",
editor = "Roger Lee",
booktitle = "Computer and Information Science",
address = "Germany",
}