基于图锚定预训练与提示的低资源文本分类增强方法
Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting
AI总结：
针对低资源文本分类标注不足的问题，提出基于图锚定预训练与提示的G2P2模型，通过图交互对比策略联合预训练图-文本模型并结合提示学习，在四个真实数据集的零/少样本任务中表现优异。
摘要：
文本分类是信息检索领域的基础问题，具备众多实际应用，例如预测在线文章主题、电商商品描述分类等。然而，标注样本极少或为零的低资源文本分类，给监督学习带来了严峻挑战。与此同时，许多文本数据天然依托网络结构存在，比如在线文章的超链接/引用网络、电商商品的用户-商品购买网络。这些图结构蕴含丰富的语义关系，有望为低资源文本分类提供增强支持。本文提出一种名为Graph-Grounded Pre-training and Prompting（G2P2，图锚定预训练与提示）的新型模型，以双路径策略解决低资源文本分类问题。预训练阶段，我们提出三种基于图交互的对比策略，联合预训练一个图-文本模型；下游分类阶段，我们为该联合预训练模型引入提示学习，以实现低资源分类。在四个真实世界数据集上开展的大量实验证明，G2P2在零样本和少样本低资源文本分类任务中具备优异性能。
英文摘要：
Text classification is a fundamental problem in information retrieval with many real-world applications, such as predicting the topics of online articles and the categories of e-commerce product descriptions. However, low-resource text classification, with few or no labeled samples, poses a serious concern for supervised learning. Meanwhile, many text data are inherently grounded on a network structure, such as a hyperlink/citation network for online articles, and a user-item purchase network for e-commerce products. These graph structures capture rich semantic relationships, which can potentially augment low-resource text classification. In this paper, we propose a novel model called Graph-Grounded Pre-training and Prompting (G2P2) to address low-resource text classification in a two-pronged approach. During pre-training, we propose three graph interaction-based contrastive strategies to jointly pre-train a graph-text model; during downstream classification, we explore prompting for the jointly pre-trained model to achieve low-resource classification. Extensive experiments on four real-world datasets demonstrate the strength of G2P2 in zero- and few-shot low-resource text classification tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
