Frame First, Then Extract: A Frame-Semantic Reasoning Pipeline for Zero-Shot Relation Triplet Extraction
Zehan Li, Fu Zhang, Wenqing Zhang, Jiawei Li, Zhou Li, Jingwei Cheng, Tianyue Peng
摘要
Large Language Models (LLMs) have shown impressive capabilities in language understanding and generation, leading to growing interest in zero-shot relation triplet extraction (Ze-roRTE), a task that aims to extract triplets for unseen relations without annotated data. However, existing methods typically depend on costly fine-tuning and lack the structured semantic guidance required for accurate and interpretable extraction. To overcome these limitations, we propose FrameRTE, a novel Ze-roRTE framework that adopts a "frame first, then extract" paradigm. Rather than extracting triplets directly, FrameRTE first constructs high-quality Relation Semantic Frames (RSFs) through a unified pipeline that integrates frame retrieval, synthesis, and enhancement. These RSFs serve as structured and interpretable knowledge scaffolds that guide frozen LLMs in the extraction process. Building upon these RSFs, we further introduce a human-inspired three-stage reasoning pipeline consisting of semantic frame evocation, frame-guided triplet extraction, and core frame elements validation to achieve semantically constrained extraction. Experiments demonstrate that FrameRTE achieves competitive zero-shot performance on multiple benchmarks. Moreover, the RSFs we construct serve as high-quality semantic resources that can enhance other extraction methods, showcasing the synergy between linguistic knowledge and foundation models. * Corresponding author. Frame ( Work ) An Agent expends effort towards achieving a Goal. Alternatively, a Salient_entity involved in the Goal can be expressed in place of a Goal expression. Definition Agent: The Agent puts effort into reaching Goal. Core Frame Elements Goal: The Goal is what the Agent expends effort to achieve. Salient_entity: An entity that is centrally involved in the Goal that the Agent is attempting to acheive. Circumstances , Degree, Depictive, Descriptor, Domain, Duration, … Non-Core Frame Elements work.n, work.v, bang away.v, plug away.v, … Lexical Units • In addition, our organization will work on improving accountability in every department. • If somebody is working on the pipes of your house and you turn on the faucet hard, you get sand, junk. • You could see several students plugging away at the problem. Demonstration Frame (Attempt) Frame (Seeking_to_achieve)
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper10
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni 等NeurIPS 2020 · 被引用 19,162 次
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu 等ICLR 2022 · 被引用 18,833 次
- GoLLIE: Annotation Guidelines improve Zero-Shot Information-ExtractionOscar Sainz, Iker García-Ferrero, Rodrigo Agerri, Oier Lopez de Lacalle 等ICLR 2024 · 被引用 168 次
- MAVEN: A Massive General Domain Event Detection DatasetXiaozhi Wang, Ziqi Wang, Xu Han, Wangyi Jiang 等EMNLP 2020 · 被引用 143 次
- Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet ExtractionQi Sun, Kun Huang, Xiaocui Yang, Rong Tong 等WWW 2024 · 被引用 40 次
相关 Paper
- A Boundary Token Graph for Zero-Shot Relation Triplet Extraction Involving Discontinuous EntitiesKailun Lyu, Zehan Li, Fu Zhang, Jingwei ChengAAAI 2026
- Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation ExtractionSizhe Zhou, Yu Meng, Bowen Jin, Jiawei HanEMNLP 2024 · 被引用 6 次
- Query Your Model with Definitions in FrameNet: An Effective Method for Frame Semantic Role LabelingCe Zheng, Yiming Wang, Baobao ChangAAAI 2023 · 被引用 6 次
- Generative Meta-Learning for Zero-Shot Relation Triplet ExtractionWanli Li, Tieyun Qian, Yi Song, Zeyu Zhang 等SIGIR 2025 · 被引用 4 次
- Reliable Data Generation and Selection for Low-Resource Relation ExtractionJunjie Yu, Xing Wang, Wenliang ChenAAAI 2024 · 被引用 7 次
