Python implementation of IJCAI 2022 Paper Global Inference with Explicit Syntactic and Discourse Structures for Dialogue-Level Relation Extraction
Install the packages as in requirement.txt
.
pip install -r requirement.txt
- Downloading the the dataset and pretrained embeddings, which are officially provided by Dialogue-Based Relation Extraction.
- Constructing Dialogue-level Mixed Dependency Graph for instances via
data/D2G_construction
. - Preparing data inputs via
data/gen_data.py
.
- Training:
python train.py \
--save_name dialogre \
--use_spemb True \
--use_wratt True \
--use_arc True
- Testing:
python test.py \
--save_name dialogre \
--use_spemb True \
--use_wratt True \
--use_arc True
Codes are based on the repos of 1) the ACL-20 Paper "Reasoning with Latent Structure Refinement for Document-Level Relation Extraction", and TASLP Paper "Relation Extraction in Dialogues: A Deep Learning Model Based on the Generality and Specialty of Dialogue Text".
@inproceedings{FeiDiaREIJCAI22,
title = {Global Inference with Explicit Syntactic and Discourse Structures for Dialogue-Level Relation Extraction},
author = {Fei, Hao and Li, Jingye and Wu, Shengqiong and Li, Chenliang and Ji, Donghong and Li, Fei},
booktitle = {Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, {IJCAI}},
pages = {4082--4088},
year = {2022},
}