# Syntactic Interchangeability in Word Embedding Models

## TL;DR

This paper examines how well word embedding models preserve syntactic interchangeability, focusing on the impact of hyper-parameters like context window size, and relates this to semantic similarity benchmarks.

## Contribution

It investigates the relationship between syntactic interchangeability and hyper-parameters in word embeddings, providing insights for better model selection based on use-case.

## Key findings

- Syntactic interchangeability varies with context window size.
- POS tags serve as effective proxies for syntactic interchangeability.
- Interchangeability correlates with performance on similarity benchmarks.

## Abstract

Nearest neighbors in word embedding models are commonly observed to be semantically similar, but the relations between them can vary greatly. We investigate the extent to which word embedding models preserve syntactic interchangeability, as reflected by distances between word vectors, and the effect of hyper-parameters---context window size in particular. We use part of speech (POS) as a proxy for syntactic interchangeability, as generally speaking, words with the same POS are syntactically valid in the same contexts. We also investigate the relationship between interchangeability and similarity as judged by commonly-used word similarity benchmarks, and correlate the result with the performance of word embedding models on these benchmarks. Our results will inform future research and applications in the selection of word embedding model, suggesting a principle for an appropriate selection of the context window size parameter depending on the use-case.