%0 Conference Proceedings %T ConvLab: Multi-Domain End-to-End Dialog System Platform %A Lee, Sungjin %A Zhu, Qi %A Takanobu, Ryuichi %A Zhang, Zheng %A Zhang, Yaoqin %A Li, Xiang %A Li, Jinchao %A Peng, Baolin %A Li, Xiujun %A Huang, Minlie %A Gao, Jianfeng %Y Costa-jussà, Marta R. %Y Alfonseca, Enrique %S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations %D 2019 %8 July %I Association for Computational Linguistics %C Florence, Italy %F lee-etal-2019-convlab %X We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments. ConvLab offers a set of fully annotated datasets and associated pre-trained reference models. As a showcase, we extend the MultiWOZ dataset with user dialog act annotations to train all component models and demonstrate how ConvLab makes it easy and effortless to conduct complicated experiments in multi-domain end-to-end dialog settings. %R 10.18653/v1/P19-3011 %U https://aclanthology.org/P19-3011 %U https://doi.org/10.18653/v1/P19-3011 %P 64-69