Learning how to Active Learn: A Deep Reinforcement Learning Approach on ShortScience.org

aclanthology.info
sci-hub
scholar.google.com

Learning how to Active Learn: A Deep Reinforcement Learning Approach
Fang, Meng and Li, Yuan and Cohn, Trevor
Empirical Methods on Natural Language Processing (EMNLP) - 2017 via Local Bibsonomy
Keywords: dblp

Summaries/Notes 1

[link] Summary by Marek Rei 7 years ago

Active learning (choosing which examples to annotate for training) is proposed as a reinforcement learning problem. The Q-learning network predicts for each sentence whether it should be annotated, and is trained based on the performance improvement from the main task. Evaluation is done on NER, with experiments on transferring the trained Q-learning function to other languages.

https://i.imgur.com/5rXm5vZ.png

Active learning (choosing which examples to annotate for training) is proposed as a reinforcement learning problem. The Q-learning network predicts for each sentence whether it should be annotated, and is trained based on the performance improvement from the main task. Evaluation is done on NER, with experiments on transferring the trained Q-learning function to other languages.

Your comment:

Write your summary here (You can use $\LaTeX$ and markdown syntax):

Anon Private