# Geometry of Compositionality

arXiv: https://arxiv.org/abs/1611.09799 · HTML: https://mlsanity.com/paper/1611.09799/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2016.

## Built on by (most cited first, 4 of 4)

- [Idiomatic Expression Identification using Semantic Compatibility](https://mlsanity.com/paper/2110.10064/) (2021)
- [Idiomatic Expression Paraphrasing without Strong Supervision](https://mlsanity.com/paper/2112.08592/) (2021)
- [From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generation](https://mlsanity.com/paper/2104.06541/) (2021)
- [Understanding Subword Compositionality of Large Language Models](https://mlsanity.com/paper/2508.17953/) (2025)

## Abstract (arXiv)

This paper proposes a simple test for compositionality (i.e., literal usage) of a word or phrase in a context-specific way. The test is computationally simple, relying on no external resources and only uses a set of trained word vectors. Experiments show that the proposed method is competitive with state of the art and displays high accuracy in context-specific compositionality detection of a variety of natural language phenomena (idiomaticity, sarcasm, metaphor) for different datasets in multiple languages. The key insight is to connect compositionality to a curious geometric property of word embeddings, which is of independent interest.