2026-06-06 –, Hardwick Hub
Multilingual embeddings are often assumed to place different languages into a shared semantic space. In practice, that alignment breaks down in systematic ways.
This talk explores where multilingual embeddings work, where they fail, and why. Using examples across multiple languages, I show how tokenisation, training data imbalance, and semantic ambiguity shape embedding behaviour in practice, along with practical diagnostics for evaluating multilingual embeddings.
Multilingual embedding models are widely used in retrieval, search, recommendation, and RAG pipelines under the assumption that semantically similar text across languages occupies a shared embedding space.
This talk examines how true that assumption is in practice.
Using pre-trained multilingual embedding models, I explore examples where multilingual alignment works extremely well, and others where it breaks down unexpectedly. Across multiple languages, we will look at how tokenisation, training data imbalance, and semantic ambiguity shape embedding geometry and retrieval behaviour.
Rather than focusing on benchmark performance, the talk emphasises intuition and failure analysis:
- Why do some languages align much more reliably than others?
- Why do averages often hide important multilingual failures?
- What happens when semantic ambiguity enters the embedding space?
Through UMAP projections, nearest-neighbour analyses, tokenisation patterns, and translation similarity distributions, we will build a practical mental model for understanding multilingual embeddings beyond the assumption of “one shared semantic space.”
The talk concludes with concrete diagnostics practitioners can use, along with common failure modes to watch for in applications.
The speaker spent over 12 years working in quantitative roles in investment management before returning to academia to study Artificial Intelligence. They are currently completing a Master’s degree in AI and ML in Science, and are particularly interested in how modern machine learning systems behave in practice, especially where modelling assumptions quietly break down.