RelationPrompt
RelationPrompt copied to clipboard
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...
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...
Bumps [lxml](https://github.com/lxml/lxml) from 4.6.5 to 4.9.1. Changelog Sourced from lxml's changelog. 4.9.1 (2022-07-01) Bugs fixed A crash was resolved when using iterwalk() (or canonicalize()) after parsing certain incorrect input. Note...
hi~, nice work I have some question. how to get the single-triplet dataset and multi-triplet dataset? Why is the accuracy rate used for single-triplet instead of F1? The model may...
有支持中文的模型吗
Hi, sorry to bother you. I was confused about the unseen label in the test set used for synthetic Data generation in step 3 and consequently leveraged the synthetic Data...
Hi~ I have some questions. How do you split the data for relation classification? What is the random seed for the split? Is it the same as the relation triplet...
 请问为什么m增大, RelationPrompt会下降