# Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell

arXiv: https://arxiv.org/abs/1809.01375 · HTML: https://mlsanity.com/paper/1809.01375/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2018.

## Built on by (most cited first, 5 of 5)

- [Local Interpretations for Explainable Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.11072/) (2021)
- [Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection](https://mlsanity.com/paper/2212.04273/) (2022)
- [COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models](https://mlsanity.com/paper/2210.01963/) (2022)
- [Interpreting Embedding Spaces by Conceptualization](https://mlsanity.com/paper/2209.00445/) (2022)
- [Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era](https://mlsanity.com/paper/2506.03994/) (2025)

## Abstract (arXiv)

This paper presents an approach for investigating the nature of semantic information captured by word embeddings. We propose a method that extends an existing human-elicited semantic property dataset with gold negative examples using crowd judgments. Our experimental approach tests the ability of supervised classifiers to identify semantic features in word embedding vectors and com- pares this to a feature-identification method based on full vector cosine similarity. The idea behind this method is that properties identified by classifiers, but not through full vector comparison are captured by embeddings. Properties that cannot be identified by either method are not. Our results provide an initial indication that semantic properties relevant for the way entities interact (e.g. dangerous) are captured, while perceptual information (e.g. colors) is not represented. We conclude that, though preliminary, these results show that our method is suitable for identifying which properties are captured by embeddings.