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

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.

arXiv commentAccepted to ACL 2019, camera-ready

References in corpus (7)

• Distributed Representations of Words and Phrases and their Compositionality
• Finding and evaluating community structure in networks
• Mixing patterns in networks
• Analysis of weighted networks
• Exploiting Similarities among Languages for Machine Translation
• A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
• Massively Multilingual Word Embeddings

Cited by in corpus (2)

• Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization
• Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification