RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction
This addresses low-resource relation extraction for knowledge representation, but it is incremental as it builds on existing prompt-based and structured text approaches.
The authors tackled the problem of extracting relation triplets (head entity, relation, tail entity) for unseen relation types, introducing the Zero-Shot Relation Triplet Extraction (ZeroRTE) task. They proposed RelationPrompt, a method using prompts to generate synthetic data, achieving strong performance on FewRel and Wiki-ZSL datasets, with results like 71.2 F1 score on FewRel.
Despite the importance of relation extraction in building and representing knowledge, less research is focused on generalizing to unseen relations types. We introduce the task setting of Zero-Shot Relation Triplet Extraction (ZeroRTE) to encourage further research in low-resource relation extraction methods. Given an input sentence, each extracted triplet consists of the head entity, relation label, and tail entity where the relation label is not seen at the training stage. To solve ZeroRTE, we propose to synthesize relation examples by prompting language models to generate structured texts. Concretely, we unify language model prompts and structured text approaches to design a structured prompt template for generating synthetic relation samples when conditioning on relation label prompts (RelationPrompt). To overcome the limitation for extracting multiple relation triplets in a sentence, we design a novel Triplet Search Decoding method. Experiments on FewRel and Wiki-ZSL datasets show the efficacy of RelationPrompt for the ZeroRTE task and zero-shot relation classification. Our code and data are available at github.com/declare-lab/RelationPrompt.