hitcszq / PAL

Policy based Active Learning with DQN

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Welcome to Learning how to Active Learn

Introduction

This source code is the basis of the following paper:

Learning how to Active Learn: A Deep Reinforcement Learning Approach, by Meng Fang, Yuan Li and Trevor Cohn, EMNLP 2017

Building

It's developed on TensorFlow.

Code

  • launcher_ner_bilingual: the starter of playing
  • game_ner: the game
  • robot: active learning policy
  • tagger

How to run

For example, we train an active learning policy on English and then apply the policy to German.

python launcher_ner_bilingual.py --agent "CNNDQN" --episode 10000 --budget 1000 --train "en.train;en.testa;en.testb;en.emb;en.model.saved" --test "de.train;de.testa;de.testb;de.emb;de.model.saved"

Data resource

About

Policy based Active Learning with DQN


Languages

Language:Python 100.0%