chapter six

6 Episodic memory for NLP

 

This chapter covers

  • Applying strongly supervised end-to-end memory networks to other sequential NLP problems than just standard Question Answering
  • Implementing a multi-hop memory network that allows for semi-supervised training
  • Comparing strongly supervised memory networks to semi-supervised memory networks

For the data we use, we will find that strongly supervised memory networks easily produce above-baseline results with very little effort. Semi-supervised memory networks produce better accuracies in a number of cases, but not consistently.

6.1 Memory networks for sequential NLP

Figure 6.1. Using memory networks for sequential NLP tasks.
mental model chapter6 memnet

6.2 Data and data processing

6.2.1 PP attachment data

6.2.2 Dutch diminutive data

6.2.3 Spanish part-of-speech data

6.3 Strongly supervised memory networks: experiments and results

6.3.1 PP-attachment

6.3.2 Dutch diminutives

6.3.3 Spanish part-of-speech tagging

6.4 Semi-supervised memory networks

6.5 Semi-supervised memory networks: experiments and results

6.6 Summary

6.7 Further reading