Information extraction with reinforcement learning, feasible?

Question

I was wondering if one could use Reinforcement Learning (as it is going to be more and more trendy with the Google DeepMind & AlphaGo's stuff) to parse and extract information from text.

For example, could it be a competitive approach to structured prediction such as

Named Entity Recognition (NER), i.e. the task of labelling New York by "city", and New York Times by "organization" Part-of-speech tagging (POS), i.e. classifying words as determinant, noun, etc. information extraction, i.e. finding and labelling some target information in texts, for instance 12/03 is date given the context meaning 3 December and has the label "expiry date" What would be a relevant modelling to do these tasks?

Rather naively I would think of a pointer that read the text from start to end and annotate each 'letter' by a label. Maybe it would learn that neighbouring letters in a 'word' share the same label, etc. Would it be able to learn long-term dependencies with this approach?

I am interested by any ideas or references related to this subject.

Answer 1

You ideally want to use Reinforcement Learning in situations where there is delayed feedback and stochastic transitions in the environment. Although you could potentially apply RL, in your case, you might be better off with a Sequence to Sequence learning framework (https://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf) since you have access to the entire sentence and there is no stochasticity involved.

On the topic of RL with Information Extraction, this might be of interest: Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning (http://arxiv.org/abs/1603.07954)

Answer 2

check this article: https://paperswithcode.com/paper/a-new-concept-of-deep-reinforcement-learning-1 with name "A New Concept of Deep Reinforcement Learning based Augmented General Tagging System"