Generative Meta-Learning for Zero-Shot Relation Triplet Extraction

作者：Wanli Li, Tieyun Qian, Yi Song, Zeyu Zhang, Jiawei Li, Zhuang Chen, Lixin Zou · 年份：2025 · DOI：10.1145/3726302.3729988 · 被引用次数：2 · 研究领域：Domain Adaptation and Few-Shot Learning、Speech Recognition and Synthesis、Natural Language Processing Techniques

Zero-shot Relation Triplet Extraction (ZeroRTE) aims to extract relation triplets from texts containing unseen relation types. This capability benefits various downstream information retrieval (IR) tasks. The primary challenge lies in enabling models to generalize effectively to unseen relation categories. Existing approaches typically leverage the knowledge embedded in pre-trained language models to accomplish the generalization process. However, these methods focus solely on fitting the training data during training, without specifically improving the model's generalization performance, resulting in limited generalization capability. For this reason, we explore the integration of bi-level optimization (BLO) with pre-trained language models for learning generalized knowledge directly from the training data, and propose a generative meta-learning framework which exploits the 'learning-to-learn' ability of meta-learning to boost the generalization capability of generative models.