Code for ACL2018 paper "Learning How to Actively Learn: A Deep Imitation Learning Approach"
This is the code for the experiment of text classification, the Active Learning (AL) policy is trained with "ALIL-simulation.py" on the source domain/language and transfered to the target domain with "ALIL-transfer.py".
If you plan to use the code, please consider to cite our paper: "Learning how to actively learn: A deep imitation learning approach Ming Liu,Wray Buntine, Gholamreza Haffari. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Pages 1874-1883, 2018".