MOSS: End-to-End Dialog System Framework with Modular Supervision

Authors: Weixin Liang, Youzhi Tian, Chengcai Chen, Zhou Yu8327-8335

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

Reproducibility Variable Result LLM Response
Research Type Experimental Based on our experiments on both Laptop Network and Cam Rest676, we summarize the take-aways for how to efficiently build a dataset to solve a task.
Researcher Affiliation Collaboration 1Zhejiang University, 2University of California, Davis, 3Stanford University, 4Xiaoi Robot Technology Co., Ltd
Pseudocode No The paper describes the architecture and formulations using mathematical equations but does not include any pseudocode or algorithm blocks.
Open Source Code Yes We release the code and data1. 1https://github.com/Youzhi Tian/MOSS-End-to-End-Dialog System-Framework-with-Modular-Supervision
Open Datasets Yes We release the code and data1. 1https://github.com/Youzhi Tian/MOSS-End-to-End-Dialog System-Framework-with-Modular-Supervision
Dataset Splits Yes We follow Wen et al. (2017b); Lei et al. (2018) to split the data as 3:1:1 for training, validation and testing.
Hardware Specification No The paper does not provide any specific details regarding the hardware used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers, such as programming language versions or library versions.
Experiment Setup No The paper describes the model architecture and formulations but does not specify concrete experimental setup details such as hyperparameter values (e.g., learning rate, batch size, number of epochs) or optimizer settings.