declare-lab/RelationPrompt
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.
PythonMIT
Issues
- 0
connection timeout error is reported when using data to generate part of the code
#21 opened by GitHubwwZ - 6
- 1
question about Algorithm 1 on step 3 and 4.
#20 opened by IoET-y - 0
how to split data for relation classification ?
#19 opened by Mizar77 - 4
Zero shot Relation classification
#8 opened by arian1995 - 1
Creating own data splits
#17 opened by jbrry - 2
Unseen Labels
#14 opened by Cishenn - 0
Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation. {'target': 250, 'success': 0, 'raw': 1}
#16 opened by Tsukiaa - 0
- 7
data limits
#13 opened by zzy1341 - 1
how to split single-triplet and multi-triplet
#10 opened by suolyer - 2
Bug in Data Splitting on FewRel Dataset
#9 opened by SaeedNajafi - 1
Demo - for line 5 and line 6 from algo
#6 opened by PinkalShah - 2
Zero Shot explanation
#7 opened by bablf - 6
Hi! I‘m trying to run this code lately. I've got a question that why there is only pretrained model for unseen=10 seed=0.WHere should I find other models? thank you
#4 opened by Drizze999