# A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings Based on Graph Modularity

## TL;DR

This paper introduces a resource-free, graph modularity-based metric to evaluate cross-lingual word embeddings, correlating well with downstream task performance and aiding unsupervised embedding improvement, especially for distant languages.

## Contribution

It proposes a novel intrinsic evaluation metric based solely on embedding structure, eliminating the need for external resources.

## Key findings

- Modularity correlates with downstream task performance.
- The metric improves unsupervised embeddings for distant language pairs.
- It provides a resource-free way to evaluate cross-lingual embeddings.

## Abstract

Cross-lingual word embeddings encode the meaning of words from different languages into a shared low-dimensional space. An important requirement for many downstream tasks is that word similarity should be independent of language - i.e., word vectors within one language should not be more similar to each other than to words in another language. We measure this characteristic using modularity, a network measurement that measures the strength of clusters in a graph. Modularity has a moderate to strong correlation with three downstream tasks, even though modularity is based only on the structure of embeddings and does not require any external resources. We show through experiments that modularity can serve as an intrinsic validation metric to improve unsupervised cross-lingual word embeddings, particularly on distant language pairs in low-resource settings.