Prompt Tuning on Graph-Augmented Low-Resource Text Classification
Gespeichert in:
| Titel: | Prompt Tuning on Graph-Augmented Low-Resource Text Classification |
|---|---|
| Autoren: | Zhihao Wen, Yuan Fang |
| Quelle: | IEEE Transactions on Knowledge and Data Engineering. 36:9080-9095 |
| Publication Status: | Preprint |
| Verlagsinformationen: | Institute of Electrical and Electronics Engineers (IEEE), 2024. |
| Publikationsjahr: | 2024 |
| Schlagwörter: | FOS: Computer and information sciences, Databases and Information Systems, Theory and Algorithms, graph, Tuning, Computer Science - Information Retrieval, low-resource learning Oils, Task analysis, Text classification, Ink, Text categorization, Paints, prompt, Accuracy, pre-training, Information Retrieval (cs.IR) |
| Beschreibung: | 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 no or few labeled samples, presents 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 handcrafted discrete prompts and continuous prompt tuning for the jointly pre-trained model to achieve zero- and few-shot classification, respectively. Moreover, we explore the possibility of employing continuous prompt tuning for zero-shot inference. Specifically, we aim to generalize continuous prompts to unseen classes while leveraging a set of base classes. To this end, we extend G2P2 into G2P2$^*$, hinging on a new architecture of conditional prompt tuning. Extensive experiments on four real-world datasets demonstrate the strength of G2P2 in zero- and few-shot low-resource text classification tasks, and illustrate the advantage of G2P2$^*$ in dealing with unseen classes. 15 pages, accepted by TKDE (IEEE Transactions on Knowledge and Data Engineering). arXiv admin note: substantial text overlap with arXiv:2305.03324 |
| Publikationsart: | Article |
| Dateibeschreibung: | application/pdf |
| ISSN: | 2326-3865 1041-4347 |
| DOI: | 10.1109/tkde.2024.3440068 |
| DOI: | 10.48550/arxiv.2307.10230 |
| Zugangs-URL: | http://arxiv.org/abs/2307.10230 |
| Rights: | IEEE Copyright arXiv Non-Exclusive Distribution CC BY NC ND |
| Dokumentencode: | edsair.doi.dedup.....d02d53bcd88e8f1ba76cf2706cd869e8 |
| Datenbank: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | 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 no or few labeled samples, presents 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 handcrafted discrete prompts and continuous prompt tuning for the jointly pre-trained model to achieve zero- and few-shot classification, respectively. Moreover, we explore the possibility of employing continuous prompt tuning for zero-shot inference. Specifically, we aim to generalize continuous prompts to unseen classes while leveraging a set of base classes. To this end, we extend G2P2 into G2P2$^*$, hinging on a new architecture of conditional prompt tuning. Extensive experiments on four real-world datasets demonstrate the strength of G2P2 in zero- and few-shot low-resource text classification tasks, and illustrate the advantage of G2P2$^*$ in dealing with unseen classes.<br />15 pages, accepted by TKDE (IEEE Transactions on Knowledge and Data Engineering). arXiv admin note: substantial text overlap with arXiv:2305.03324 |
|---|---|
| ISSN: | 23263865 10414347 |
| DOI: | 10.1109/tkde.2024.3440068 |