A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings Based on Graph Modularity
This provides a resource-free evaluation method for cross-lingual word embeddings, particularly benefiting low-resource language processing, though it is incremental as it adapts an existing graph metric.
The paper tackled the problem of evaluating cross-lingual word embeddings without external resources by proposing modularity as a metric, showing it correlates with downstream tasks and improves embeddings for distant language pairs in low-resource settings.
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.