Document-level Relation Extraction via Subgraph Reasoning

Authors: Xingyu Peng, Chong Zhang, Ke Xu

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on Doc RED show that SGR outperforms existing models, and further analyses demonstrate that our method is both effective and explainable. Our code is available at https://github.com/Crysta1ovo/SGR.
Researcher Affiliation Academia Xingyu Peng , Chong Zhang and Ke Xu State Key Lab of Software Development Environment, Beihang University, Beijing, 100191, China {xypeng, chongzh, kexu}@buaa.edu.cn
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code Yes Our code is available at https://github.com/Crysta1ovo/SGR.
Open Datasets Yes We evaluate our model on Doc RED, a large-scale humanannotated dataset for document-level RE constructed from Wikipedia and Wikidata.
Dataset Splits Yes Doc RED contains 3,053 documents for training, 1,000 for development, and 1,000 for testing, involving 96 relation types, 132,275 entities, and 56,354 relational facts.
Hardware Specification No No specific hardware details (e.g., GPU models, CPU types, or memory) used for running experiments are provided in the paper.
Software Dependencies No While the paper mentions using GloVe, Bi LSTM, and AdamW, it does not specify the version numbers for these or any other software libraries, environments, or programming languages used.
Experiment Setup Yes With setting the batch size to 4, we train our model using Adam W [Loshchilov and Hutter, 2019] optimizer, a linear learning rate scheduler with 6% warmup, and a maximum learning rate of 0.01. All hyperparameters are tuned based on the development set.