This repository implements our ACL Findings 2022 research paper RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction. The goal of Zero-Shot Relation Triplet Extraction (ZeroRTE) is to extract relation triplets of the format (head entity, tail entity, relation), despite not having annotated data for the test relation labels.
Hello, Thanks a ton for the help.
I was wondering where we are suppose to pass the input data(in the form of "context: s") while predict for an complete unseen sentence.
Hi, for inference of the relation extractor model, you can pass in the path of the data in a json file, based on the code demo and image below. The data file should follow the same format as the existing data .
Hello, Thanks a ton for the help. I was wondering where we are suppose to pass the input data(in the form of "context: s") while predict for an complete unseen sentence.