What Happens Next? Future Subevent Prediction Using Contextual Hierarchical LSTM

Authors: Linmei Hu, Juanzi Li, Liqiang Nie, Xiao-Li Li, Chao Shao

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on a real-world dataset demonstrate the superiority of our model over several state-of-the-art methods.
Researcher Affiliation Academia 1 Department of Computer Science and Technology, Tsinghua University, China 2 School of Computer Science and Technology, Shandong University, China 3 Institute for Infocomm Research, A*STAR, Singapore
Pseudocode No The paper describes the model architecture and steps but does not provide structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described in this paper.
Open Datasets Yes We therefore crawled a large-scale Chinese news event dataset containing 15,254 news series from Sina News2. 2http://news.sina.com.cn/zt/
Dataset Splits Yes After preprocessing, we randomly split all the events into three parts: 80% for training, 10% for validation and the remaining 10% for test.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions "ICTCLAS3" and "SRILM tool (Stolcke and others 2002)" but does not provide specific version numbers for these or other software dependencies.
Experiment Setup Yes The optimal parameter values are given as follows. 1) LSTM parameters and word embedding were initialized from a uniform distribution between [-0.08, 0.08]; 2) Learning rate = 0.1; 3) Batch size = 32; 4) Dropout rate = 0.2; 5) The dimension of word embeddings and topic embeddings = 100, and the dimension of hidden vector D = 400; 6) The number of hidden layers of the LSTM networks = 2; 7) The topic number = 1,000.