# Learning Conceptual Space Representations of Interrelated Concepts

arXiv: https://arxiv.org/abs/1805.01276 · HTML: https://mlsanity.com/paper/1805.01276/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2018.

## Built on by (most cited first, 3 of 3)

- [KnAC: an approach for enhancing cluster analysis with background knowledge and explanations](https://mlsanity.com/paper/2112.08759/) (2021)
- [A Factorized Probabilistic Model of the Semantics of Vague Temporal Adverbials Relative to Different Event Types](https://mlsanity.com/paper/2505.01311/) (2025)
- [Region-Based Merging of Open-Domain Terminological Knowledge](https://mlsanity.com/paper/2205.02660/) (2022)

## Abstract (arXiv)

Several recently proposed methods aim to learn conceptual space representations from large text collections. These learned representations asso- ciate each object from a given domain of interest with a point in a high-dimensional Euclidean space, but they do not model the concepts from this do- main, and can thus not directly be used for catego- rization and related cognitive tasks. A natural solu- tion is to represent concepts as Gaussians, learned from the representations of their instances, but this can only be reliably done if sufficiently many in- stances are given, which is often not the case. In this paper, we introduce a Bayesian model which addresses this problem by constructing informative priors from background knowledge about how the concepts of interest are interrelated with each other. We show that this leads to substantially better pre- dictions in a knowledge base completion task.