# Neural Vector Conceptualization for Word Vector Space Interpretation

## TL;DR

This paper introduces a neural method to interpret word vectors by activating higher order concepts directly in the original space, improving understanding of NLP models.

## Contribution

It presents a novel neural approach that interprets word vectors through non-linear concept activation, operating directly in the original vector space.

## Key findings

- Produces less entropic concept activation profiles than cosine similarity
- Capable of learning non-linear relations between vectors and concepts
- Operates directly in the original vector space

## Abstract

Distributed word vector spaces are considered hard to interpret which hinders the understanding of natural language processing (NLP) models. In this work, we introduce a new method to interpret arbitrary samples from a word vector space. To this end, we train a neural model to conceptualize word vectors, which means that it activates higher order concepts it recognizes in a given vector. Contrary to prior approaches, our model operates in the original vector space and is capable of learning non-linear relations between word vectors and concepts. Furthermore, we show that it produces considerably less entropic concept activation profiles than the popular cosine similarity.