Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization

Authors: Xiachong Feng, Xiaocheng Feng, Bing Qin, Xinwei Geng

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on AMI and ICSI meeting datasets show that our full system can achieve SOTA performance
Researcher Affiliation Academia Xiachong Feng , Xiaocheng Feng , Bing Qin , Xinwei Geng Harbin Institute of Technology, China {xiachongfeng, xcfeng, bqin, xwgeng}@ir.hit.edu.cn
Pseudocode No The paper describes its model architecture using diagrams and mathematical equations, but it does not include a distinct 'Pseudocode' or 'Algorithm' block.
Open Source Code Yes Our codes and outputs are available at: https://github.com/xcfcode/DDAMS/.
Open Datasets Yes We experiment on AMI [Carletta et al., 2005] and ICSI [Janin et al., 2003] datasets.
Dataset Splits Yes We preprocess the dataset into train, valid and test sets for AMI (97/20/20) and ICSI (53/25/6) separately following Shang et al. [2018].
Hardware Specification No The paper discusses model architecture and training but does not specify any particular hardware (e.g., GPU models, CPU types) used for experiments.
Software Dependencies No The paper mentions using a 'SOTA dialogue discourse parser', 'Bi LSTM', and 'Py Rouge package' but does not specify their version numbers or other software dependencies with versions.
Experiment Setup No The paper describes the model architecture and training objective but does not provide specific experimental setup details such as learning rates, batch sizes, or optimizer settings.