Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph

Authors: Hao Fei, Shengqiong Wu, Meishan Zhang, Yafeng Ren, Donghong Ji

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

Reproducibility Variable Result LLM Response
Research Type Experimental 5 Experimentation. Table 1: Main results on three datasets. Table 2: Ablation results on Du Conv dataset.
Researcher Affiliation Academia 1Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, China 2Institute of Computing and Intelligence, Harbin Institute of Technology (Shenzhen), China 3Laboratory of Language and Artificial Intelligence, Guangdong University of Foreign Studies, China
Pseudocode No The paper describes methods using mathematical equations and textual explanations, but no formal pseudocode or algorithm blocks are provided.
Open Source Code No The paper does not provide any statement or link regarding the public availability of its source code.
Open Datasets Yes We conduct experiments on three CSRL datasets [Xu et al., 2021], including Du Conv, News Dialog and Personal Dialog
Dataset Splits Yes Du Conv has the 80%/10%/10% ratio of train/dev/test
Hardware Specification No The paper does not specify any hardware details such as GPU or CPU models used for the experiments.
Software Dependencies No The paper mentions software components like BERT, Dia BERT, GCN, and Adam optimizer, but no specific version numbers are provided for reproducibility.
Experiment Setup Yes GCN hidden size is set as 350. We adopt Adam as the optimizer with an initial learning rate of 5e-4 with weight decay of 1e-5. The initial α value is 1.5. To alleviate overfitting, we use a dropout rate of 0.5 on the input layer and the output layer.