Modeling Dense Cross-Modal Interactions for Joint Entity-Relation Extraction

Authors: Shan Zhao, Minghao Hu, Zhiping Cai, Fang Liu

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiment results on Co NLL04 dataset show that our model obtains state-of-the-art results by achieving 90.62% F1 on entity recognition and 72.97% F1 on relation classification. In ADE dataset, our model surpasses existing approaches by more than 1.9% F1 on relation classification. Extensive analyses further confirm the effectiveness of our approach.
Researcher Affiliation Academia Shan Zhao1 , Minghao Hu2 , Zhiping Cai1 and Fang Liu3 1College of Computer, National University of Defense Technology, Changsha, China 2PLA Academy of Military Science, Beijing, China 3School of Design, Hunan University, Changsha, Hunan
Pseudocode No The paper describes the model architecture and processing steps using text and diagrams, but it does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any statement about making its source code publicly available or provide a link to a code repository for the described methodology.
Open Datasets Yes To evaluate the performance of our model, we conduct experiments on two datasets. The first one is the Co NLL04 dataset [Roth and Yih, 2004]... The second one is the ADE dataset [Gurulingappa et al., 2012].
Dataset Splits Yes To directly compare with previous works, we evaluate our model using 10-fold cross-validation similar to prior approaches on the ADE dataset [Li et al., 2017; Bekoulis et al., 2018]. ... We regularize our network using dropout with a rate tuned on the development set (the dropout rate is 0.2 for embeddings, 0.1 and 0.3 for Bi LSTM on two datasets respectively).
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments, such as GPU models, CPU types, or memory specifications.
Software Dependencies No The paper mentions software components like "Adam optimizer" and "Bi LSTM", but does not specify version numbers for these or other key software dependencies (e.g., Python, PyTorch, TensorFlow versions) that would be needed for replication.
Experiment Setup Yes We regularize our network using dropout with a rate tuned on the development set (the dropout rate is 0.2 for embeddings, 0.1 and 0.3 for Bi LSTM on two datasets respectively). We utilize 2 BSA units in our network (m=2) and set the dimensionality of hidden size d as 128. We choose 25 as the dimensionality of label embeddings dl. The size of character embeddings is 128, while the dimensionality of ELMo [Peters et al., 2018] is 1024. Adam optimizer with a learning rate of 0.0005 is used to optimize parameters. The training takes 180 epochs for convergence.