Few-Shot Semantic Dependency Parsing via Graph Contrastive Learning
Bin Li, Yunlong Fan, Yikemaiti Sataer, Chuanqi Shi, Miao Gao, Zhiqiang Gao
Abstract
Graph neural networks (GNNs) have achieved promising performance on semantic dependency parsing (SDP), owing to their powerful graph representation learning ability. However, training a high-performing GNN-based model requires a large amount of labeled data and it is prone to over-fitting in the absence of sufficient labeled data. To address this drawback, we propose a syntax-guided graph contrastive learning framework to pre-train GNNs with plenty of unlabeled data and fine-tune pre-trained GNNs with few-shot labeled SDP data. Through extensive experiments conducted on the SemEval-2015 Task 18 English dataset in three formalisms (DM, PAS, and PSD), we demonstrate that our framework achieves promising results when few-shot training samples are available. Furthermore, benefiting from the pre-training process, our framework exhibits notable advantages in the out-of-domain test sets.
BibTeX
@inproceedings{li-etal-2024-shot-semantic,
title = "Few-Shot Semantic Dependency Parsing via Graph Contrastive Learning",
author = "Li, Bin and
Fan, Yunlong and
Sataer, Yikemaiti and
Shi, Chuanqi and
Gao, Miao and
Gao, Zhiqiang",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.636/",
pages = "7248--7258"
}