ayyyq/DORE

code for [EMNLP22 findings] DORE: Document Ordered Relation Extraction based on Generative Framework

Python

4 commits

updated Sep 11, 2024

See the code

README

DORE: Document Ordered Relation Extraction based on Generative Framework

The paper is accepted to Findings of EMNLP 2022.

Requirements

transformers==4.16.2

Experiments

To run the code, change the parameters as you need and use

bash run.sh

~~We have offered a checkpoint for DORE + negative sampling_digonal + distant, since it takes a long time (about 7 days) to pre-train on the distantly supervised dataset. Please download it from here.~~ Due to storage limitations, we no longer provide our checkpoint. Sorry for any inconvinence.

Similar repos

jzhang38/LPD

code for EMNLP 2022 paper Better Few-Shot Relation Extraction with Label Prompt Dropout

Xianjun-Yang/FewDocAE

Few-Shot Document-Level Event Argument Extraction: https://arxiv.org/abs/2209.02203

thunlp/NREPapers

Must-read papers on neural relation extraction (NRE)

1,021

thunlp/RE-Context-or-Names

Bert-based models(BERT, MTB, CP) for relation extraction.

103

Babelscape/rebel

REBEL is a seq2seq model that simplifies Relation Extraction (EMNLP 2021).

578

MiuLab/PairDistill

Source code of our paper "PairDistill: Pairwise Relevance Distillation for Dense Retrieval", EMNLP…

UKPLab/acl2024-dapr

cl-tohoku/xbe

Cross-stitch bi-encoder for distantly supervised relation extraction (EMNLP 2022)