Modular Mechanistic Networks On Bridging Mechanistic And Phenomenological Models With Deep Neural Networks In Natural Language Processing

# Modular Mechanistic Networks: On Bridging Mechanistic and Phenomenological Models with Deep Neural Networks in Natural Language Processing

**arXiv ID:** 1807.09844
**Authors:** Simon Dobnik, John D. Kelleher
**Published:** 2018-07-21T11:37:15Z
**Abstract:**
Natural language processing (NLP) can be done using either top-down (theory driven) and bottom-up (data driven) approaches, which we call mechanistic and phenomenological respectively. The approaches are frequently considered to stand in opposition to each other. Examining some recent approaches in deep learning we argue that deep neural networks incorporate both perspectives and, furthermore, that leveraging this aspect of deep learning may help in solving complex problems within language technology, such as modelling language and perception in the domain of spatial cognition.

## Skill Description

This skill is generated from the arXiv paper: Modular Mechanistic Networks: On Bridging Mechanistic and Phenomenological Models with Deep Neural Networks in Natural Language Processing (1807.09844).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:1807.09844](http://arxiv.org/abs/1807.09844v2)